MindDory Brain

Profile snapshot: CEFR level, target/source languages, due card count, weak words, recent lookups. Pass `lang` to scope the snapshot to one learning language (for users learning several); omit it for the user's primary language.

{
  "type": "object",
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional ISO or BCP-47 tag (en, en-us, pt-br). Scopes the whole profile - level, due count, weak words - to that learning language. Omit for the user's primary language."
    }
  },
  "additionalProperties": false
}

Call this at the START of every new conversation, before your first reply, to load the user's Minddory setup and your role as their proactive language partner: CEFR level, target/source languages, due-card count, weak words, and how to capture. The user connected Minddory to actively improve their language through this chat, so use it to tailor your help to their level and goals. Pass `lang` when you know which language the user wants to practice right now - the language they are conversing in, or one they named explicitly (including a regional variant like en-us or en-gb) - so the returned profile is scoped to that language. Re-call this tool with the new `lang` if the user switches practice language or requests a specific variant mid-conversation.

{
  "type": "object",
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional ISO or BCP-47 tag of the language the user wants to practice in this conversation (en, en-us, de, pt-br). Defaults to the user's primary learning language."
    }
  },
  "additionalProperties": false
}

Words the user has verified known via flashcard practice. Paginated keyset on flashcards.id.

{
  "type": "object",
  "properties": {
    "lang": {
      "type": "string",
      "description": "Language tag of the words: base ISO with an optional region (en, en-us, pt-br). Omit it and the user's own primary learning language is used."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "cursor": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

Cards due now and due within the next 24 hours.

{
  "type": "object",
  "properties": {
    "lang": {
      "type": "string",
      "description": "Language tag of the queue: base ISO with an optional region (en, en-us, pt-br). Omit it and the user's own primary learning language is used."
    },
    "max": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    }
  },
  "additionalProperties": false
}

Single card detail by word (case-insensitive). Returns translation, mastery, and last 10 events.

{
  "type": "object",
  "properties": {
    "word": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "lang": {
      "type": "string",
      "description": "Language tag of the word: base ISO with an optional region (en, en-us, pt-br). Omit it and the user's own primary learning language is used."
    }
  },
  "required": [
    "word"
  ],
  "additionalProperties": false
}

Event log slice with optional surface filter and keyset pagination on answers.id.

{
  "type": "object",
  "properties": {
    "surface": {
      "type": "string",
      "description": "e.g. 'claude_mcp', 'app', 'cursor_mcp'"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "cursor": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

Append a generic interaction event to the answers log. Use for lookups, AI discussions, and reading-in-context signals.

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "lookup",
        "discussed",
        "read_in_context"
      ]
    },
    "word": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "lang": {
      "type": "string",
      "description": "Language tag of the word: base ISO with an optional region (en, en-us, pt-br). Scoped on the base, so the variant the session instructions ask you to send always matches. Omit it and the user's own primary learning language is used."
    },
    "metadata": {
      "type": "object",
      "additionalProperties": true
    }
  },
  "required": [
    "type",
    "word"
  ],
  "additionalProperties": false
}

Confidence-weighted spaced-repetition boost when the user has used a word correctly: the card moves further out in the review schedule. Logs an answer row even if no flashcard exists.

{
  "type": "object",
  "properties": {
    "word": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "lang": {
      "type": "string",
      "description": "Language tag of the word: base ISO with an optional region (en, en-us, pt-br). Scoped on the base, so the variant the session instructions ask you to send always matches. Omit it and the user's own primary learning language is used."
    },
    "confidence": {
      "type": "string",
      "enum": [
        "high",
        "medium",
        "low"
      ]
    },
    "source": {
      "type": "string",
      "maxLength": 100
    },
    "context": {
      "type": "string",
      "maxLength": 2000
    }
  },
  "required": [
    "word",
    "confidence"
  ],
  "additionalProperties": false
}

Spaced-repetition degrade for a word the user just got wrong: the card comes back sooner. ease_factor drops, interval resets, repetitions reset.

{
  "type": "object",
  "properties": {
    "word": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "lang": {
      "type": "string",
      "description": "Language tag of the word: base ISO with an optional region (en, en-us, pt-br). Scoped on the base, so the variant the session instructions ask you to send always matches. Omit it and the user's own primary learning language is used."
    },
    "source": {
      "type": "string",
      "maxLength": 100
    },
    "context": {
      "type": "string",
      "maxLength": 2000
    }
  },
  "required": [
    "word"
  ],
  "additionalProperties": false
}

Capture a target-language word or phrase to the user's Minddory vocabulary deck (a flashcard in the "Chat Discoveries" folder when the word is new, otherwise a context encounter). The user connected Minddory so their assistant builds their deck from real conversations, so use this proactively to log notable target-language vocabulary they encounter, use, or ask about. By connecting Minddory the user opted IN to automatic capture, so just capture as you chat - do not pause to ask permission for each word, and do not turn capturing into a yes/no question. You do not need to announce each capture, but answer honestly if the user asks what you have saved. Use the `words` array to capture several from one message; include a `gloss` (short source-language translation) and `context` (the sentence) when you can. Skip stop words, proper nouns, numbers, and words shorter than 3 characters (CJK / Hangul exempt). ALWAYS pass `lang` — the ISO code of the captured word's own language (you know it from the conversation); the call is rejected without it and the target language is never guessed. `source_lang` (the user's native language) is optional and defaults to their deck. This is the primary tracking signal of Minddory, so capture diligently.

{
  "type": "object",
  "properties": {
    "word": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Single-word capture (legacy). Use `words` for more than one."
    },
    "gloss": {
      "type": "string",
      "maxLength": 500,
      "description": "Short translation in the source language. Strongly recommended."
    },
    "context": {
      "type": "string",
      "maxLength": 2000,
      "description": "The sentence where the word appeared."
    },
    "words": {
      "type": "array",
      "maxItems": 50,
      "description": "Batch capture. Each entry is {word, gloss?, context?}. Prefer this when capturing 2+ words from the same message.",
      "items": {
        "type": "object",
        "required": [
          "word"
        ],
        "properties": {
          "word": {
            "type": "string",
            "minLength": 1,
            "maxLength": 200
          },
          "gloss": {
            "type": "string",
            "maxLength": 500
          },
          "context": {
            "type": "string",
            "maxLength": 2000
          }
        }
      }
    },
    "lang": {
      "type": "string",
      "description": "REQUIRED. ISO code of the captured word's own language (en, de, es, zh, ...). The call is rejected if omitted — never leave it blank or guess from prior context."
    },
    "source_lang": {
      "type": "string",
      "description": "ISO code of the user's native/source language. Optional — defaults to the source language of the user's existing deck."
    }
  },
  "additionalProperties": false
}

Log a grammar mistake the user just made in the target language, creating a grammar point in their Minddory deck. Use it proactively whenever the user writes a target-language sentence with a clear, correctable error (wrong tense, agreement, word_choice, word_order, missing or wrong article, preposition, gender, conjugation, spelling, pluralization). By connecting Minddory the user opted IN to automatic capture, so log it as you go - do not ask permission first or turn it into a yes/no question. The user connected Minddory to catch and review these patterns; you do not need to announce each log. Pass the original text + correction + error_type. Multiple mistakes in one message = multiple calls. VARIANT RULE: Always pass the user's full BCP-47 variant in the lang field (e.g. en-gb, not en) - get it from get_system_instructions on first turn. Before logging, check that the "error" is not actually a valid regional variant form (US past-simple vs UK present-perfect with "just/already", US "in the hospital" vs UK "in hospital", US "color" vs UK "colour", BR gerund vs PT "a + infinitive", etc.). When the variant is unspecified (base ISO only), treat ALL regional forms as valid. Better to skip a borderline call than to mark a valid variant form as wrong. error_type must be one of: tense, agreement, word_choice, word_order, article, preposition, spelling, pluralization, conjugation, gender, other. Feeds the user's Grammar Patterns view at app.minddory.com/grammar.

{
  "type": "object",
  "properties": {
    "user_text": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The exact erroneous sentence/phrase the user wrote."
    },
    "correction": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The corrected sentence/phrase."
    },
    "error_type": {
      "type": "string",
      "maxLength": 40,
      "description": "One of: tense, agreement, word_choice, word_order, article, preposition, spelling, pluralization, conjugation, gender, other."
    },
    "explanation": {
      "type": "string",
      "maxLength": 1000,
      "description": "Short rationale (1-2 sentences). Optional."
    },
    "lang": {
      "type": "string",
      "description": "ISO target language code."
    }
  },
  "required": [
    "user_text",
    "correction"
  ],
  "additionalProperties": false
}

Get the user's most actively encountered target-language words (from past capture_word + log_interaction events), ranked by frequency over a lookback window. Use to surface "frontier" words the user keeps touching when they ask "what should I learn next" or when you want context-aware suggestions.

{
  "type": "object",
  "properties": {
    "lang": {
      "type": "string",
      "description": "Language tag (en, en-us, pt-br). Matching is on the base code, so a variant finds encounters logged under any sibling. Omit it to include ALL languages - unlike the deck tools, this one is a cross-language frequency view."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Default 20."
    },
    "lookback_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 365,
      "description": "Default 30."
    }
  },
  "additionalProperties": false
}

Batch lookup: for a list of target-language words, tell me which ones are already in the user's Minddory deck and how well they know each. Use this BEFORE glossing or capturing vocabulary from a message - it answers "which of these are actually new to this user" in one call, so you can skip words they have already mastered, gloss only the genuinely new ones, and notice when a word they are currently failing shows up in conversation. Each result is {word, in_deck, mastery, translation, next_review_at, due}; mastery is one of not_in_deck, new, review, struggling, mastered. The response also pulls out the three lists you usually act on - `not_in_deck`, `known` and `struggling` - so you do not have to sort them yourself; words in mid-review are in `words` only. Entries that could not be answered as sent are listed in `skipped` as {input, reason: blank|duplicate, answered_as?} - a duplicate WAS answered, under the entry named by `answered_as`. Omit `lang` and it resolves to the user's own primary learning language (`lang_defaulted: true` in the response says so); pass it whenever you know which language you are in. Prefer this over calling get_card once per word.

{
  "type": "object",
  "properties": {
    "words": {
      "type": "array",
      "minItems": 1,
      "maxItems": 50,
      "description": "The words or phrases to check, as written in the target language.",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 200
      }
    },
    "lang": {
      "type": "string",
      "description": "Language tag of the words: a base ISO code with an optional region (en, en-us, es-419). Three-subtag tags such as zh-Hant-TW are not accepted. Omit it and the user's own primary learning language is used."
    }
  },
  "required": [
    "words"
  ],
  "additionalProperties": false
}