Skip to main content
Glama

memory_search

Read-only

Search stored project and global memories to recall user preferences, commands, decisions, and gotchas before asking questions you may have already answered.

Instructions

Search memories. Use before asking the user something they may have told you.

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": "memory_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNo
limitNodefault 5
queryYes
scopeNodefault all (global + this project)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.5/5.0
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 and locality are covered by structured data. The description adds the behavioral inference that lookups are cheap enough to run proactively before asking the user, but says nothing about matching semantics (keyword vs semantic), result ordering, or what an empty result means. With annotations carrying the safety profile, this is adequate but thin.

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?

Two sentences, zero filler, with the action front-loaded before the usage trigger. Nothing could be removed without losing information.

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?

For a four-parameter search tool with an enum filter and no output schema, the definition is minimally sufficient: it tells the agent what it does and when to reach for it. It omits the shape and ordering of results and the meaning of the type filter, which an agent would need to interpret hits correctly.

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

Parameters2/5

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

Schema description coverage is only 50%: 'query' and the nine-value 'type' enum carry no descriptions at all. The definition says nothing about how query text is matched or when filtering by type is worthwhile, so it does not compensate for the coverage gap. The only documented parameters (limit, scope) already explain themselves in the 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?

The description states a specific verb and resource ('Search memories'), so an agent knows immediately that this is a retrieval operation over stored memories. It does not explicitly distinguish itself from the sibling memory_context, which likely also returns memory content, leaving some ambiguity about which retriever to pick.

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?

'Use before asking the user something they may have told you' gives a concrete, actionable trigger condition, which is more than most definitions offer. It stops short of naming alternatives or stating when not to use it (e.g., when a full context load via memory_context is preferable), so it is clear but not exhaustive.

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