Skip to main content
Glama

Search memory

search_memory
Read-onlyIdempotent

Search the user's Thread memory to find matching notes with short snippets. Call catch_up first at the start of a new conversation, then query to recall relevant saved notes and chat logs.

Instructions

Search the user's Thread memory. Returns matching notes with a short snippet. (At the start of a new conversation, call catch_up first.)

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_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds a genuinely useful conversational prerequisite (catch_up first) and a hint about result granularity ('short snippet'), but says nothing about matching behavior, result limits, or ranking. It does not contradict the annotations.

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

Conciseness4/5

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

Two short sentences with no filler, and the core purpose is front-loaded. The prerequisite sits in a trailing parenthetical, which buries an important sequencing rule slightly, but overall the description is efficiently sized.

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?

An output schema exists, so return values need not be described, and the tool is a simple single-parameter search. However, an agent still lacks any sense of what 'Thread memory' holds, how matching works, or how results are ordered/limited, which matters for a search tool choosing among recall siblings.

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?

The schema has one required parameter, 'query', with 0% description coverage, so the schema itself explains nothing about it. The description does not clarify whether the query is natural language, keyword-based, or fuzzy, nor what fields of a memory it matches against, leaving the parameter's semantics largely unstated.

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

Purpose4/5

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

The description names a specific verb and resource ('Search the user's Thread memory') and states the return shape ('matching notes with a short snippet'). It does not explicitly distinguish itself from close siblings like list_memory or read_note, so differentiation is left partly implicit.

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?

One concrete usage rule is given: at the start of a new conversation, call `catch_up` first. Beyond that prerequisite there is no guidance on when to search versus list or read a note directly, and no exclusions, so the when-to-use picture is only partially filled in.

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