ShowMeOnMap

Create a new workspace from a natural-language query. Returns a map_id you can pass to mutate_map or get_state for follow-up actions. For the full Op catalog and predicate grammar that downstream tools (mutate_map, filter_layer, etc.) accept, fetch the MCP resource at showmeonmap://docs/workspace-ops-spec — do NOT guess the shapes.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Natural language: \"coffee shops in Tokyo\", \"GDP by country\", \"volcanoes in Indonesia\", etc."
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "query",
    "rationale"
  ]
}

Apply a natural-language instruction to an existing workspace. Valid mutations: filter a layer, remove a layer, change camera, change basemap. For ambiguous instructions the tool emits a clarification field. For unrelated instructions it emits outOfScope — build a new map in that case. For the full Op catalog and predicate grammar, fetch the MCP resource showmeonmap://docs/workspace-ops-spec.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "map_id from a prior build_map call"
    },
    "instruction": {
      "type": "string",
      "minLength": 1,
      "description": "e.g., \"filter to where magnitude is greater than 5\", \"change basemap to dark\""
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "instruction",
    "rationale"
  ]
}

Return the current workspace, map plan, and active filters for a given map_id.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "rationale"
  ]
}

Append a fully-constructed LayerPlan to an existing workspace without going through NL. Pass the same shape the workspace pipeline emits — { id, title, source, viz, geometry, ... }. Prefer this when you already have a structured plan; otherwise use mutate_map. For the full LayerPlan and Op spec, fetch the MCP resource showmeonmap://docs/workspace-ops-spec.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1,
      "description": "map_id from a prior build_map call"
    },
    "layerPlan": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Full LayerPlan object. Must include id, title, source, viz, geometry."
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    },
    "intent": {
      "description": "Optional. Which mental model is this add_layer operating under? \"primary-data\" = the layer the user actually asked to see; \"context-overlay\" = supporting data layered on top of a primary; \"reference-boundary\" = admin/geo boundary used as a backdrop; \"annotation\" = caller-placed callout / pin layer; \"comparison\" = a layer added to compare against another; \"other\" = none of the above.",
      "type": "string",
      "enum": [
        "primary-data",
        "context-overlay",
        "reference-boundary",
        "annotation",
        "comparison",
        "other"
      ]
    }
  },
  "required": [
    "map_id",
    "layerPlan",
    "rationale"
  ]
}

Spatially join two existing layers and add a new layer that encodes both values per region as a 3x3 bivariate choropleth. Both layers must already exist in the workspace (call build_map or add_layer first). Auto-detects the numeric value field from each layer's viz config; pass value_field_a / value_field_b to override. Returns the new layer_id, correlation r, and matched-feature count. Required: map_id, layer_a_id, layer_b_id, rationale.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_a_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_b_id": {
      "type": "string",
      "minLength": 1
    },
    "mode": {
      "default": "bivariate",
      "type": "string",
      "const": "bivariate"
    },
    "value_field_a": {
      "type": "string"
    },
    "value_field_b": {
      "type": "string"
    },
    "new_layer_id": {
      "type": "string"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layer_a_id",
    "layer_b_id",
    "rationale"
  ]
}

Spatially join two existing workspace layers and return the Pearson correlation coefficient r, sample size n, two-sided p-value approximation, plus human-readable strength and direction labels. Pure read — no layer is added, no op is committed, no credit charge. Use this when you want a numeric answer without rendering; use add_fusion_layer when the user wants the visualization. Required: map_id, layer_a_id, layer_b_id, rationale.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_a_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_b_id": {
      "type": "string",
      "minLength": 1
    },
    "value_field_a": {
      "type": "string"
    },
    "value_field_b": {
      "type": "string"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layer_a_id",
    "layer_b_id",
    "rationale"
  ]
}

Narrow a layer to features matching a structured predicate. `append:true` (default) conjoins with any existing filter; `append:false` replaces the chain.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1,
      "description": "id of the layer to filter"
    },
    "predicate": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Predicate in the Mongo-shape grammar. Examples: {op:\"eq\",field:\"category\",value:\"cafe\"}, {op:\"gt\",field:\"magnitude\",value:5}, {op:\"within\",geometry:{type:\"Polygon\",coordinates:[...]}}, {op:\"and\",children:[...]}. See docs/superpowers/specs/2026-04-17-workspace-ops-log-design.md §6."
    },
    "append": {
      "description": "Default true. false replaces the layer's existing filter chain.",
      "type": "boolean"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    },
    "intent": {
      "description": "Optional. Which mental model is this filter operating under? \"narrow\" = generic shrink-the-set; \"isolate-outliers\" = pull out anomalies for inspection; \"compare-subset\" = pre-step before a side-by-side compare; \"preview-data\" = exploratory peek; \"other\" = none of the above.",
      "type": "string",
      "enum": [
        "narrow",
        "isolate-outliers",
        "compare-subset",
        "preview-data",
        "other"
      ]
    }
  },
  "required": [
    "map_id",
    "layerId",
    "predicate",
    "rationale"
  ]
}

Create a new layer containing the source layer's features that lie within the supplied polygon. The source layer is untouched. Useful for "show me only the X inside this country/bbox/hand-drawn shape."

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "sourceLayerId": {
      "type": "string",
      "minLength": 1
    },
    "newLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "Id for the new layer. Must not already be in use in this workspace."
    },
    "selection": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "Polygon",
            "MultiPolygon"
          ]
        },
        "coordinates": {
          "type": "array",
          "items": {}
        }
      },
      "required": [
        "type",
        "coordinates"
      ],
      "description": "GeoJSON Polygon or MultiPolygon in [lng,lat] coordinate order."
    },
    "inheritStyle": {
      "description": "Default true. false emits a new layer with minimal default styling.",
      "type": "boolean"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "sourceLayerId",
    "newLayerId",
    "selection",
    "rationale"
  ]
}

Refine an existing layer to a NAMED area the server resolves from OpenStreetMap — a street corridor ("Broadway from Arbutus Street to Main Street"), a place ("Mount Pleasant"), or an intersection surroundings. Pass names only, never coordinates; unresolvable names return a clarification with real nearby candidates instead of guessed geometry. Emits ordinary undoable ops (filter / new layer + camera) and a grounded summary like "kept 37 of 150 features". Costs 1 credit when a mutation lands; clarifications are refunded.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "areaRef": {
      "oneOf": [
        {
          "type": "object",
          "properties": {
            "kind": {
              "type": "string",
              "const": "place"
            },
            "name": {
              "type": "string",
              "minLength": 1
            }
          },
          "required": [
            "kind",
            "name"
          ]
        },
        {
          "type": "object",
          "properties": {
            "kind": {
              "type": "string",
              "const": "corridor"
            },
            "street": {
              "type": "string",
              "minLength": 1
            },
            "from": {
              "type": "string",
              "minLength": 1
            },
            "to": {
              "type": "string",
              "minLength": 1
            },
            "bufferMeters": {
              "type": "number",
              "minimum": 30,
              "maximum": 1000
            }
          },
          "required": [
            "kind",
            "street"
          ]
        },
        {
          "type": "object",
          "properties": {
            "kind": {
              "type": "string",
              "const": "aroundIntersection"
            },
            "street": {
              "type": "string",
              "minLength": 1
            },
            "cross": {
              "type": "string",
              "minLength": 1
            },
            "radiusMeters": {
              "type": "number",
              "minimum": 50,
              "maximum": 5000
            }
          },
          "required": [
            "kind",
            "street",
            "cross"
          ]
        }
      ]
    },
    "mode": {
      "description": "filter (default): hide features outside, reversible. select: copy matches into a new layer. clip: new layer with geometry trimmed at the boundary.",
      "type": "string",
      "enum": [
        "filter",
        "select",
        "clip"
      ]
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layerId",
    "areaRef",
    "rationale"
  ]
}

Compute a spatial analysis server-side and append the finished, honestly-legended result as a new layer + camera; the result REPLACES its input layer(s) (undoable). hotspot = Getis-Ord Gi*: hot/cold significance classes (99/95/90%, Benjamini-Hochberg FDR-corrected) on a numeric field, or on hex-binned point density when valueField is omitted. zonal = aggregate points into polygon zones (an existing zone layer OR a generated h3 fishnet): count/sum/mean/min/max per zone as a quantile choropleth where zero and no-data are distinct classes. enrich = join a US Census ACS indicator (median income, home value, rent, …) onto each feature by tract/county/state containment — unmatched features stay null, never zero-filled. join = spatial join (attribute transfer): each point in layerId takes properties from the joinLayerId polygon containing it (collisions prefixed, unmatched points carry NO joined fields, zero overlap is a typed rejection). merge = append two same-geometry-class layers into one dataset with a per-row source column (schemas never null-filled; class mismatch is a typed failure). near = nearest-neighbor distance columns (great-circle meters, stated — never presented as road distance). dissolve = true polygon union per attribute group (missing values form their own group; partial sums reported). Returns a grounded memo + stats payload — every number is computed, never generated; findings keep the map. Costs 1 credit when the result lands; typed failures (unknown layer, too few features, >10,000-feature cap) are refunded.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "analysis": {
      "type": "string",
      "enum": [
        "hotspot",
        "zonal",
        "enrich",
        "join",
        "merge",
        "near",
        "dissolve"
      ],
      "description": "Which analysis to run. 'hotspot' = Getis-Ord Gi* with FDR-corrected significance classes. 'zonal' = aggregate a point layer into polygon zones (count/sum/mean/min/max choropleth). 'enrich' = join a US Census indicator onto each feature by containment (tract/county/state). 'join' = spatial join (attribute transfer): each POINT in layerId takes the listed properties from the polygon in joinLayerId that contains it — the aggregate direction (points INTO polygons) is 'zonal'. 'merge' = append layerId + mergeLayerId (same geometry class) into ONE dataset, each row stamped with its source layer. 'near' = each POINT in layerId gains the great-circle distance to (and identity of) its nearest feature in nearLayerId. 'dissolve' = union POLYGONS sharing a dissolveField value into single features (omit the field to dissolve all into one)."
    },
    "layerId": {
      "type": "string",
      "minLength": 1,
      "description": "The workspace layer to analyze (geojson-backed; the point source for zonal; the point TARGET for join; the styling donor for merge)."
    },
    "valueField": {
      "description": "Numeric property to analyze. hotspot: omit on point layers for incident-DENSITY mode (hex-binned counts). zonal: omit for count-only aggregation.",
      "type": "string",
      "minLength": 1
    },
    "k": {
      "description": "hotspot only: nearest neighbors per feature (default 8).",
      "type": "integer",
      "minimum": 3,
      "maximum": 24
    },
    "hexMeters": {
      "description": "hotspot density mode only: hex cell spacing in meters (default auto from the data extent).",
      "type": "number",
      "minimum": 100,
      "maximum": 50000
    },
    "zoneLayerId": {
      "description": "zonal only: an existing polygon layer to aggregate into. Provide EXACTLY ONE of zoneLayerId or zones.",
      "type": "string",
      "minLength": 1
    },
    "zones": {
      "description": "zonal only: generate an h3 hex fishnet over the source extent instead of using a zone layer (resolution 3-10, default auto). Provide EXACTLY ONE of zoneLayerId or zones.",
      "type": "object",
      "properties": {
        "kind": {
          "type": "string",
          "const": "h3"
        },
        "resolution": {
          "type": "integer",
          "minimum": 3,
          "maximum": 10
        }
      },
      "required": [
        "kind"
      ],
      "additionalProperties": false
    },
    "stats": {
      "description": "zonal only: which statistics to attach per zone (default: count, plus sum/mean/min/max when valueField is set).",
      "minItems": 1,
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "count",
          "sum",
          "mean",
          "min",
          "max"
        ]
      }
    },
    "indicator": {
      "description": "enrich only (required there): a US Census ACS preset id (e.g. 'median_household_income', 'median_home_value', 'median_rent') or a raw ACS variable code (e.g. 'B19013_001E').",
      "type": "string",
      "minLength": 1,
      "maxLength": 80
    },
    "geoLevel": {
      "description": "enrich only: containment geography (default tract). Tract/county fetch only the states the data touches, capped at 3 — filter first or use state for wider layers.",
      "type": "string",
      "enum": [
        "state",
        "county",
        "tract"
      ]
    },
    "joinLayerId": {
      "description": "join only (required there): the POLYGON layer providing the attributes.",
      "type": "string",
      "minLength": 1
    },
    "fields": {
      "description": "join only: which join-layer properties to transfer (default: auto-select up to 12 non-internal properties, overflow reported).",
      "minItems": 1,
      "maxItems": 12,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 80
      }
    },
    "prefix": {
      "description": "join only: prefix for a joined field whose name collides with an existing target property (default \"join_\").",
      "type": "string",
      "minLength": 1,
      "maxLength": 20
    },
    "mergeLayerId": {
      "description": "merge only (required there): the second layer — same geometry class (point/line/polygon) as layerId.",
      "type": "string",
      "minLength": 1
    },
    "sourceField": {
      "description": "merge only: name of the per-row provenance column naming each row's source layer (default \"merge_source\"; renamed on collision, reported).",
      "type": "string",
      "minLength": 1,
      "maxLength": 40
    },
    "nearLayerId": {
      "description": "near only (required there): the POINT layer to search for each target point's nearest neighbor.",
      "type": "string",
      "minLength": 1
    },
    "nearField": {
      "description": "near only: property of the nearest feature to copy as its identity (default: first name-like property).",
      "type": "string",
      "minLength": 1,
      "maxLength": 80
    },
    "maxDistanceM": {
      "description": "near only: search radius in meters — a point whose nearest neighbor is farther carries NO near fields (reported).",
      "type": "number",
      "minimum": 1,
      "maximum": 20000000
    },
    "dissolveField": {
      "description": "dissolve only: group-by property (omit = dissolve ALL into one footprint); missing values form their own \"(no value)\" group.",
      "type": "string",
      "minLength": 1,
      "maxLength": 80
    },
    "sumFields": {
      "description": "dissolve only: numeric properties to SUM per group — skipped values reported, a group with none present carries NO sum.",
      "minItems": 1,
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 80
      }
    },
    "annotate": {
      "description": "Opt-in: place ONE callout annotation at the headline feature (hottest cluster / top zone / highest value). Label text comes only from computed values.",
      "type": "boolean"
    },
    "story": {
      "description": "Opt-in: persist the shared map with a 2-step story rail (grounded overview + analysis memo isolating the result layer) — the /m/ link opens with it.",
      "type": "boolean"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "analysis",
    "layerId",
    "rationale"
  ]
}

Evaluate a predicate against a layer's inline features and return the matching subset. No Op is emitted and the workspace is not mutated. Handy for introspection ("how many X match Y?") before deciding whether to filter, subset, or build a new layer.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "predicate": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Predicate in the Mongo-shape grammar. Examples: {op:\"eq\",field:\"category\",value:\"cafe\"}, {op:\"gt\",field:\"magnitude\",value:5}, {op:\"within\",geometry:{type:\"Polygon\",coordinates:[...]}}, {op:\"and\",children:[...]}. See docs/superpowers/specs/2026-04-17-workspace-ops-log-design.md §6."
    },
    "limit": {
      "description": "Default 100, max 1000. Response sets `truncated:true` when clipped.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 1000
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layerId",
    "predicate",
    "rationale"
  ]
}

Drop a layer from the workspace by id. Strict: removing an already-removed or never-added layer fails. Layer ids do NOT recycle — a removed id cannot be re-added later in the same workspace. GATED: this tool is destructive. Pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    },
    "confirmed": {
      "description": "Set to true to confirm this destructive action. If omitted or false, the call returns a needs_confirmation envelope. Layer ids are tombstoned — once removed, the same id cannot be re-added later in this workspace.",
      "type": "boolean"
    }
  },
  "required": [
    "map_id",
    "layerId",
    "rationale"
  ]
}

Wipe every predicate currently applied to a layer's filter chain, making every source feature visible again. Inverse of filter_layer. No-op on layers that have no existing filter. GATED: pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    },
    "confirmed": {
      "description": "Set to true to confirm this sensitive action. If omitted or false, the call returns a needs_confirmation envelope. Wiping a filter chain is recoverable via undo, but autonomous agents lack a UI surface to confirm intent.",
      "type": "boolean"
    }
  },
  "required": [
    "map_id",
    "layerId",
    "rationale"
  ]
}

Change a layer's id from oldLayerId to newLayerId. Re-keys any existing filter chain and preserves insertion order among sibling layers. Strict: newLayerId must not already be in use (current OR tombstoned) in this workspace. Subsequent ops must reference the layer by its new id.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "oldLayerId": {
      "type": "string",
      "minLength": 1
    },
    "newLayerId": {
      "type": "string",
      "minLength": 1,
      "description": "New id. Must be unique within the workspace."
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "oldLayerId",
    "newLayerId",
    "rationale"
  ]
}

Adjust a layer's color and/or opacity. Within-palette changes only — the renderer silently ignores fields the current viz variant doesn't support. Pass at least one of color / opacity; passing neither is an accepted no-op.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layerId": {
      "type": "string",
      "minLength": 1
    },
    "color": {
      "description": "CSS color string: hex (#RRGGBB), rgb/rgba, or named color.",
      "type": "string",
      "minLength": 1
    },
    "opacity": {
      "description": "0 (transparent) to 1 (opaque).",
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layerId",
    "rationale"
  ]
}

Override the workspace camera. Latest set_camera op wins during replay. Two modes: `fitBounds` with a [w,s,e,n] bbox (plus optional padding/animateMs), or `flyTo` with [lng,lat] center + zoom (plus optional pitch/bearing/animateMs). Use for "zoom to Japan", "center on Paris at z=10", or finishing a drill-down after filter_layer. Equivalent to the camera move mutate_map would emit, but skips the NL roundtrip.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "camera": {
      "oneOf": [
        {
          "type": "object",
          "properties": {
            "mode": {
              "type": "string",
              "const": "fitBounds"
            },
            "bounds": {
              "type": "array",
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                },
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "description": "[west, south, east, north] bbox in WGS84 degrees."
            },
            "padding": {
              "description": "Pixel padding around the bbox. Default is the renderer default.",
              "type": "number",
              "minimum": 0
            },
            "animateMs": {
              "description": "Animation duration in ms. 0 = instant jump.",
              "type": "number",
              "minimum": 0
            }
          },
          "required": [
            "mode",
            "bounds"
          ]
        },
        {
          "type": "object",
          "properties": {
            "mode": {
              "type": "string",
              "const": "flyTo"
            },
            "center": {
              "type": "array",
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "description": "[lng, lat] in WGS84."
            },
            "zoom": {
              "type": "number"
            },
            "pitch": {
              "description": "Tilt in degrees, 0-60.",
              "type": "number"
            },
            "bearing": {
              "description": "Rotation in degrees, 0-360.",
              "type": "number"
            },
            "animateMs": {
              "description": "Animation duration in ms. 0 = instant jump.",
              "type": "number",
              "minimum": 0
            }
          },
          "required": [
            "mode",
            "center",
            "zoom"
          ]
        }
      ]
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "camera",
    "rationale"
  ]
}

Override the current time-range filter. Latest set_time op wins during replay. Use for "filter to 2020-2024" or "show only the last 7 days" intents. Not yet consumed by the renderer — the UI drives the slider directly — but the value is captured in the ops log and queryable via get_state.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "field": {
      "type": "string",
      "minLength": 1,
      "description": "Feature property carrying the time value (e.g. \"date\", \"year\", \"timestamp\")."
    },
    "rangeStart": {
      "type": "number",
      "description": "Inclusive lower bound of the visible window."
    },
    "rangeEnd": {
      "type": "number",
      "description": "Inclusive upper bound of the visible window."
    },
    "format": {
      "description": "How rangeStart/rangeEnd encode time. Default: unix_ms at render time.",
      "type": "string",
      "enum": [
        "unix_ms",
        "iso",
        "integer"
      ]
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "field",
    "rangeStart",
    "rangeEnd",
    "rationale"
  ]
}

Label the current workspace state with a user-supplied name. The label is mirrored into workspace.meta.tags so UIs can render a named-revision history. Tagging the same label twice is idempotent — no error, no duplicate entry.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Checkpoint label, e.g. \"before EV layer added\" or \"v1.0\"."
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "name",
    "rationale"
  ]
}

Add a user-placed label at a specific coordinate. Annotations are independent of layers and live in their own id namespace. Strict: the id must not already be in use by another CURRENTLY-placed annotation (removed ids can be recycled).

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "Stable id for this annotation — caller-supplied."
    },
    "coords": {
      "type": "array",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "description": "[lng, lat] in WGS84."
    },
    "label": {
      "description": "Optional text rendered at the point.",
      "type": "string"
    },
    "color": {
      "description": "Optional CSS color for the marker + label.",
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "id",
    "coords",
    "rationale"
  ]
}

Drop a previously-placed annotation by id. Strict: removing an already-removed or never-placed id fails. After removal, the id CAN be re-used by a later add_annotation (unlike layer ids, which are tombstoned for the session).

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "annotationId": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "annotationId",
    "rationale"
  ]
}

Return the current workspace document (ops log + cursor + meta) plus the materialized mapPlan and layerFilters, in a shape suitable for save-to-file / share-by-URL / inspection. Pure read — no mutation, no credit charge. Use this when you want the full raw state for serialization; use get_state when you want the compact envelope for display.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "rationale"
  ]
}

Export a single layer's features as a downloadable file. Returns a URL with Content-Disposition: attachment so the user's browser downloads it. CSV drops geometry beyond a (lng, lat) centroid — for full polygon/line geometry, use format: "geojson". The URL is an unguessable capability link that does NOT expire — treat it as shareable-forever, not temporary. Required: map_id, layer_id, format, rationale.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "layer_id": {
      "type": "string",
      "minLength": 1
    },
    "format": {
      "type": "string",
      "enum": [
        "csv",
        "geojson"
      ]
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "layer_id",
    "format",
    "rationale"
  ]
}

Returns a deep-link URL that opens the map in the user's browser and automatically triggers a PNG download. The user clicks the link, the browser renders the map at full resolution with the legend composited (if legend: true), and the file downloads. There is no server-side rendering; the user's browser is the renderer. Required: map_id, rationale. Optional: format (png default), legend (true default).

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "format": {
      "default": "png",
      "type": "string",
      "enum": [
        "png",
        "jpeg",
        "pdf"
      ]
    },
    "legend": {
      "default": true,
      "type": "boolean"
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "rationale"
  ]
}

Rewind the workspace cursor by one, re-materializing the state as it was before the last mutation. Does NOT delete any ops — redo will fast-forward. Calling undo at the workspace genesis (cursor === 0, only the CreateWorkspace op is in scope) is a no-op that surfaces an error rather than silently doing nothing. GATED: pass confirmed:true to proceed; otherwise a needs_confirmation envelope is returned.

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    },
    "confirmed": {
      "description": "Set to true to confirm this sensitive action. If omitted or false, the call returns a needs_confirmation envelope. Autonomous undo without user intent is a footgun — an agent that decides to \"fix\" something can erase prior work.",
      "type": "boolean"
    }
  },
  "required": [
    "map_id",
    "rationale"
  ]
}

Advance the workspace cursor by one toward the tail of the ops log, replaying the next op that was previously undone. Calling redo when the cursor is already at the tail (no undone ops to fast-forward) fails rather than silently no-op. Note: any new op applied via apply-op / mutate-map after an undo truncates the redo tail (standard edit-stack semantics).

{
  "type": "object",
  "properties": {
    "map_id": {
      "type": "string",
      "minLength": 1
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "map_id",
    "rationale"
  ]
}

Tell the ShowMeOnMap team your agent hit something it could not accomplish — an unsupported intent, a missing tool, an unclear schema, an op that failed in a confusing way. Use this when build_map / mutate_map / a direct-op tool returns something you cannot recover from, OR when you would have wanted a different tool to exist. Records the report to a server-side log; does not unblock the current session, but feeds future capability work. No map_id required — file the report even if no map was built.

{
  "type": "object",
  "properties": {
    "map_id": {
      "description": "Optional. The map_id you were working on, if any.",
      "type": "string",
      "minLength": 1
    },
    "what_i_was_trying": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "High-level intent in one or two sentences. e.g. \"merge two filtered choropleths into a fused bivariate map\"."
    },
    "what_i_tried": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1000,
      "description": "Which tools / inputs you attempted, in order. Be specific — tool name + key arg shape is ideal."
    },
    "where_i_got_stuck": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "The specific failure: what came back, what was missing, why you could not proceed."
    },
    "suggested_capability": {
      "description": "Optional. A new tool, op, or schema field that would have unblocked you.",
      "type": "string",
      "minLength": 1,
      "maxLength": 300
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "what_i_was_trying",
    "what_i_tried",
    "where_i_got_stuck",
    "rationale"
  ]
}

Save a re-runnable, parameterized workflow: an ordered list of natural-language instructions (step 1 builds, later steps mutate). Wrap values in {braces} and declare them in params. Running it later re-executes the instructions on FRESH data and bills per step like typing.

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 80,
      "description": "Workflow name."
    },
    "steps": {
      "minItems": 1,
      "maxItems": 12,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "instruction": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4000
          }
        },
        "required": [
          "instruction"
        ]
      },
      "description": "Ordered NL instructions. Step 1 builds the map; later steps mutate it. Wrap values in {braces} to declare parameters."
    },
    "params": {
      "description": "Declared parameters — every {slot} used in steps must be declared here.",
      "maxItems": 8,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "minLength": 1,
            "maxLength": 40
          },
          "label": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "kind": {
            "type": "string",
            "enum": [
              "place",
              "number",
              "text",
              "timerange"
            ]
          },
          "default": {
            "type": "string",
            "maxLength": 200
          }
        },
        "required": [
          "name",
          "label",
          "kind"
        ]
      }
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "name",
    "steps",
    "rationale"
  ]
}

List the caller's saved workflows with their parameters and per-run credit estimates.

{
  "type": "object",
  "properties": {
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "rationale"
  ]
}

Execute a saved workflow with parameter values. PAID: bills ~1 credit per step through the normal build/mutate paths (the estimate is in list_workflows). Optional batch mode sweeps ONE param across 2–20 values — each value is a full independent run (steps × values credits); failed/paused values are reported per value and the batch continues. A clarification pauses a single run (status "paused" + the question); failures stop at the failing step. On success the result is a live map with a shareable URL (batch: the last successful value's map).

{
  "type": "object",
  "properties": {
    "workflow_id": {
      "type": "string",
      "minLength": 1,
      "description": "From save_workflow or list_workflows."
    },
    "params": {
      "description": "Values for the workflow's declared parameters.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": "string"
      }
    },
    "batch": {
      "description": "Batch mode: run the workflow once per value (\"each of the 12 districts\"). Bills steps × values.",
      "type": "object",
      "properties": {
        "param": {
          "type": "string",
          "minLength": 1,
          "description": "The ONE declared param to sweep (must not also be in params)."
        },
        "values": {
          "minItems": 2,
          "maxItems": 20,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "description": "2–20 values; each is a FULL independent billed run."
        }
      },
      "required": [
        "param",
        "values"
      ]
    },
    "rationale": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "Short audit-log label (≤300 chars) stating the user-facing goal this call serves, e.g. \"add wildfire layer for the user's California query\". Required on every call. Stored in the operations log so map edits stay traceable — we never see your chat history."
    }
  },
  "required": [
    "workflow_id",
    "rationale"
  ]
}