Skip to main content
Glama

search_messages

Search a project's messages by subject and body using full-text queries with phrase, prefix, and boolean support to find relevant conversations and context.

Instructions

Full-text search over subject and body for a project.

Tips

  • SQLite FTS5 syntax supported: phrases ("build plan"), prefix (mig*), boolean (plan AND users)

  • Results are ordered by bm25 score (best matches first)

  • Limit defaults to 20; raise for broad queries

Query examples

  • Phrase search: "build plan"

  • Prefix: migrat*

  • Boolean: plan AND users

  • Require urgent: urgent AND deployment

Parameters

project_key : str Project identifier. query : str FTS5 query string. limit : int Max results to return.

Returns

list[dict] Each entry: { id, subject, importance, ack_required, created_ts, thread_id, from }

Example

{"jsonrpc":"2.0","id":"10","method":"tools/call","params":{"name":"search_messages","arguments":{
  "project_key":"/abs/path/backend","query":""build plan" AND users", "limit": 50
}}}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
formatNo
agent_nameNo
project_keyYes
registration_tokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.4

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses bm25 ordering, the default limit of 20, and the exact return fields, but says nothing about authentication/registration needs even though parameters like registration_token and agent_name exist and are unexplained.

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

Conciseness3/5

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

Purpose is front-loaded and the structure is scannable, but it is padded: the same query examples appear in both the Tips list and the Query examples section, and the large JSON-RPC example duplicates information already given in the Parameters block.

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

Completeness3/5

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

With no output schema the description correctly supplies a Returns section with field names, which is a real strength. However it leaves three parameters undocumented and gives no guidance on auth/registration context, so it is only partially complete for a six-parameter tool.

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 description coverage is 0%, so the description must compensate. It does document project_key, query and limit in one-liners, but three of six parameters (format, agent_name, registration_token) are undocumented in both the schema and the description.

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, resource and scope: full-text search over message subject and body within a project. It is clearly distinguishable from list-oriented siblings like fetch_inbox/fetch_topic and summarization tools like summarize_thread.

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

Usage Guidelines3/5

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

The Tips and Query examples sections explain how to build FTS5 queries (phrases, prefix, boolean) and advise raising limit for broad queries, but never says when to prefer this tool over fetch_inbox, fetch_topic, or summarize_thread. Usage is implied rather than routed.

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