quarry

Overview Schema Source Related Servers Discussions Admin

find

Search local documents and code by meaning, combining vector similarity and full-text search to retrieve relevant results. Use before web searches or when answering why/how questions.

Instructions

Use find before WebSearch or WebFetch for research, or before answering a why/how/what-did-we-decide question. Prefer grep for symbol and value lookups; prefer find for meaning.

Combines vector similarity and BM25 full-text search via Reciprocal Rank Fusion (RRF) for better recall on both meaning and exact terms.

Args: query: Natural language search query. limit: Maximum number of results (default 10, max 50). document_filter: Optional exact document name to filter by. collection: Optional collection name to search within. page_type: Optional content type filter (text, code, spreadsheet, etc.). source_format: Optional source format filter (.pdf, .py, .xlsx, etc.). agent_handle: Your own handle to recall only your memories (e.g. "rmh"); leave empty to search everything. memory_type: Optional memory type filter (fact, observation, lesson, etc.).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes
`page_type`	No
`collection`	No
`memory_type`	No
`agent_handle`	No
`source_format`	No
`document_filter`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.0Aug 3, 2026

TDQS

A4.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description does substantive behavioral work: it explains the hybrid vector/BM25 search with RRF and clarifies agent_handle scoping ('leave empty to search everything'). It does not explicitly state read-only/no side effects, but search semantics and the output schema make this largely clear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The usage guidance is front-loaded, the RRF sentence justifies the search behavior without fluff, and the Args block is dense but necessary given the schema's lack of descriptions. Every part of the description earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter search tool with no annotations, the description covers when to use it, how the search works, all parameter semantics, and limits. The output schema is present, so return-value details are reasonably deferred.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description defines all eight parameters with real meaning: query as natural language, limit with default/max, exact document filter, collection, content type, source format, own-memory scoping, and memory type. This fully compensates for the empty schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies find as a semantic search tool for memories/knowledge, positioned against WebSearch, WebFetch, and grep. The distinction 'prefer grep for symbol and value lookups; prefer find for meaning' makes its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit trigger conditions: use before WebSearch or WebFetch for research, before answering why/how/what-did-we-decide questions, and prefer grep when doing symbol/value lookups. This is directly actionable selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server