Skip to main content
Glama

memory_search

Read-onlyIdempotent

Search local research experience across permitted projects using terms, aliases, and conditions to find and validate evidence for reuse, without running new computations.

Instructions

Find local research experience across permitted projects using terms, aliases and conditions. Similarity selects evidence; validation_match decides reuse. No new computation occurs.

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": {
      "task_id": "<task_id>"
    },
    "name": "memory_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
task_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral context beyond them: results are similarity-ranked evidence rather than validated facts, and 'No new computation occurs' confirms it is passive retrieval with no side effects. It does not describe result shape, but an output schema exists to cover that.

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 short sentences, keyword-dense and front-loaded: purpose first, ranking semantics second, safety assurance third. No filler or repetition.

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 rich annotations and an output schema, the main gaps are the unexplained required task_id and the limit default, plus no statement of what 'permitted projects' means practically. Adequate for a retrieval tool, but not fully self-contained for a first-time caller.

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 coverage is 0%, so the description must carry the load, and 'terms, aliases and conditions' meaningfully characterizes what the query string matches rather than merely restating the parameter name. It does not spell out limit or why task_id is required, but it adds genuine semantics beyond the bare schema.

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?

States a specific verb and resource ('Find local research experience') and scopes it to 'permitted projects', which tells an agent what corpus is searched. 'Research experience' is somewhat abstract jargon, but the verb+resource pairing is unambiguous enough to distinguish it from memory_get or memory_rebuild.

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 line 'Similarity selects evidence; validation_match decides reuse' implicitly routes the agent: use search to gather candidates, use validation_match to actually reuse them. There is no explicit when-to-use or when-not guidance, and no statement of prerequisites (e.g., what 'permitted projects' requires).

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