Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_knowledge_search

Read-only

Search knowledge documents by full-text to recall what is already known before starting work; returns ranked snippets with pagination and supports prefix matching.

Instructions

Full-text search (SQLite FTS5) over the titles and bodies of the latest revision of every knowledge document, including ingested maps. All words must match; end a word with * for a prefix match. Returns ranked hits with a snippet, paginated; fetch a full document with grove_knowledge_get. Use before starting work, to recall what is already known. Grove is local only: scans are read-only and nothing is sent to GitHub or any other service.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "grove_knowledge_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPage size (default 50, max 200).
queryYesWords to search for.
offsetNoNumber of items to skip.
projectNoOnly documents of this project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/destructiveHint/openWorldHint annotations by disclosing the matching rule (all words must match), prefix syntax, ranked results with snippets, pagination, and the local-only read-only scan guarantee with nothing sent externally. That query-semantics and data-locality detail is exactly what annotations cannot convey.

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?

Four tight sentences, front-loaded with what it searches and the matching semantics, then results shape, then the alternative tool, then the safety note. No filler or restated title, and every clause contributes usable information.

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?

With no output schema available, the description still describes the return shape (ranked hits with a snippet, paginated), which is the main gap it needed to close. Query syntax, escalation path, and safety profile are all present for a four-parameter read tool.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics for the core parameter that the terse schema entry 'Words to search for' lacks: implicit AND across words and trailing-* prefix matching. limit/offset/project remain covered only by the schema, which is acceptable given full coverage.

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?

States a specific mechanism (SQLite FTS5 full-text search) over a specific resource (titles and bodies of the latest revision of every knowledge document, including ingested maps), which is far more informative than a generic 'search' claim. It explicitly separates itself from the sibling that returns whole documents via 'fetch a full document with grove_knowledge_get'.

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

Usage Guidelines4/5

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

Gives concrete timing guidance ('Use before starting work, to recall what is already known') and routes the agent to grove_knowledge_get when a full document is needed. It does not state an explicit when-not-to-use case or mention other siblings, so it stops short of full alternative coverage.

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

Deploy Server

Other Tools