Skip to main content
Glama
CROW: LLM Wiki

CROW: LLM Wiki

Official

search

Read-only

Find notes matching a query and return ranked paths, titles, and summaries to read yourself. Use for keywords, names, codes, or quoted phrases; use recall for answers.

Instructions

Find the notes whose words best match a query, best first, with no answer written.

Use it for a name, a code, a quoted phrase or keywords when you will read the notes yourself with read_note; to get an answer to a question, use recall. Fast: no model is called. Returns up to k notes, each with its path, title, summary and rank.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoHow many notes, 1 to 50
queryYesWords to look for, or a quoted expression, a code, a name
whereNoOptional: only notes with all these values, e.g. {"team": "ops"}

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.5
    • changedInput schema / properties / where / description
      Previous value: -"Only notes whose fields have all these values, e.g. {\"team\": \"ops\"}"New value: +"Optional: only notes with all these values, e.g. {\"team\": \"ops\"}"
  2. First observedv1.0.4

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral facts — no model is called, so it is fast and produces no written answer — which annotations cannot express. It also restates the return shape, but that overlaps the existing output schema, keeping this short of the top band.

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?

Three tight sentences: purpose and ranking first, then routing to read_note/recall, then cost and return shape. No filler, and the distinguishing scope is front-loaded rather than buried.

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 a three-parameter read tool with a full output schema and annotations, nothing material is missing: intent, alternatives, cost profile and result contents are all covered. The agent can decide to call it and interpret the result without opening the schema.

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

Parameters3/5

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

Schema coverage is 100%, so query, k and where are all documented in structured fields; baseline is 3. The description echoes query semantics (name, code, quoted phrase) and k ("up to k notes") but says nothing about the `where` filter beyond what the schema already states.

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 verb and resource ("Find the notes whose words best match a query"), plus the ranking order ("best first") and the key negative scope ("no answer written"). That last clause distinguishes it immediately from an answer-producing sibling.

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?

Gives explicit when-to-use cases (a name, a code, a quoted phrase or keywords) tied to a precondition ("when you will read the notes yourself with `read_note`") and names the alternative for a different intent ("to get an answer to a question, use `recall`"). When-not guidance is present, not just when.

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