Pakistan Case Law

Full-text search of Pakistani judgments (Supreme Court & High Courts, 1970 onward). Ranking follows how lawyers research: nearness to the legal point decides which cases are returned; among comparably-near cases, more senior court > larger bench > more recent > more cited. Use sort='newest' when you need the current state of the law (later judgments supersede as statutes are amended), or sort='court' for the most authoritative first. Returns ranked cases with id, title, citation, court, year, a snippet, and the public URL. For an exact report citation use caselaw_lookup_citation. To read a case, pass its id to caselaw_get_case.

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Keywords, e.g. 'bail murder 302' or 'khula dower'",
      "maxLength": 200,
      "minLength": 2,
      "title": "Query",
      "type": "string"
    },
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "sort": {
      "default": "relevance",
      "description": "relevance (default: nearest on the point, then court/bench/recency/citations) | newest (latest law first — useful because amendments supersede) | court (most senior court first)",
      "title": "Sort",
      "type": "string"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "query"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_searchArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_searchOutput"
}

Find judgments by the QUESTION they settle, rather than by words they contain. Every AI summary on this corpus records the questions that judgment actually decides — e.g. "Does delay in lodging the FIR by itself entitle the accused to bail?" This searches those questions, so it matches the shape a legal problem arrives in rather than the vocabulary a 1987 bench happened to use. COVERAGE IS PARTIAL: only some judgments have an AI summary with questions yet (the response's `coverage_note` gives the current live ratio, which keeps growing). An empty result means no *summarised* judgment matched — it does NOT mean no such judgment exists. Fall back to caselaw_search, which covers the whole corpus. The questions are written by an AI reading the judgment. They are a finding aid, not a holding: cite the judgment, never the question. Pass an id to caselaw_get_case to read it.

{
  "type": "object",
  "properties": {
    "query": {
      "description": "The legal question or its subject, in the words a judgment would use — 'delay in lodging FIR', 'concurrent findings of fact', 'pre-arrest bail murder'",
      "maxLength": 200,
      "minLength": 2,
      "title": "Query",
      "type": "string"
    },
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "query"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_search_questionsArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_search_questionsOutput"
}

Find the judgment(s) at an exact law-report citation. Example: journal='PLD', year=1995, page=34 → PLD 1995 Supreme Court 34. Omit page to list everything reported in that journal+year. Returns the same case shape as caselaw_search.

{
  "type": "object",
  "properties": {
    "journal": {
      "description": "Law-report code, e.g. 'PLD', 'SCMR', 'CLC'",
      "maxLength": 30,
      "minLength": 1,
      "title": "Journal",
      "type": "string"
    },
    "year": {
      "maximum": 2100,
      "minimum": 1900,
      "title": "Year",
      "type": "integer"
    },
    "page": {
      "anyOf": [
        {
          "minimum": 1,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Page/serial number in the report (optional)",
      "title": "Page"
    },
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "journal",
    "year"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_lookup_citationArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_lookup_citationOutput"
}

Fetch one judgment by id. section='summary' (default) returns metadata + the AI headnote (plain-language summary, the laws/provisions referred, and keyword tags) — read this first to judge relevance cheaply. section='full' additionally returns the judgment body text (capped at ~40,000 chars; the response flags body_truncated/body_chars_total when longer).

{
  "type": "object",
  "properties": {
    "case_id": {
      "description": "Numeric judgment id (from a search/lookup/graph result)",
      "minimum": 1,
      "title": "Case Id",
      "type": "integer"
    },
    "section": {
      "$ref": "#/$defs/Section",
      "default": "summary",
      "description": "'summary' = metadata + AI headnote (cheap); 'full' = + judgment text"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "case_id"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    },
    "Section": {
      "enum": [
        "summary",
        "full"
      ],
      "title": "Section",
      "type": "string"
    }
  },
  "title": "caselaw_get_caseArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_get_caseOutput"
}

Walk the citation graph FORWARD: list the in-corpus cases that THIS judgment cites (the precedents it relied on). Combine with caselaw_get_cited_by to traverse precedent backward and forward until a research question is resolved. Most useful on RECENT judgments: a 2024-25 case usually has nobody citing it yet, but its own citation list is a curated map of the established authority on the point.

{
  "type": "object",
  "properties": {
    "case_id": {
      "description": "Numeric judgment id",
      "minimum": 1,
      "title": "Case Id",
      "type": "integer"
    },
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "case_id"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_get_citationsArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_get_citationsOutput"
}

Walk the citation graph BACKWARD: list later cases that cite THIS judgment (how it was subsequently treated — followed, distinguished, relied upon). Returns newest first. Most useful on OLDER or landmark judgments: it shows whether the case is still followed and where the principle has been applied since. A leading case can have hundreds of citing cases.

{
  "type": "object",
  "properties": {
    "case_id": {
      "description": "Numeric judgment id",
      "minimum": 1,
      "title": "Case Id",
      "type": "integer"
    },
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "required": [
    "case_id"
  ],
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_get_cited_byArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_get_cited_byOutput"
}

List the most-cited (landmark) judgments in the corpus, ranked by how many other cases cite them. A good entry point for the leading authorities on Pakistani law.

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    },
    "response_format": {
      "$ref": "#/$defs/Fmt",
      "default": "markdown"
    }
  },
  "$defs": {
    "Fmt": {
      "enum": [
        "markdown",
        "json"
      ],
      "title": "Fmt",
      "type": "string"
    }
  },
  "title": "caselaw_most_citedArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "caselaw_most_citedOutput"
}