Skip to main content
Glama

Search memories

memory_search
Read-onlyIdempotent

Search stored memories to retrieve ranked raw hits for a query; use optional bank scope and limit to narrow results.

Instructions

Return ranked raw hits from stored memories. memory_recall suits questions; memory_reflect synthesizes an answer.

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
bankNoOptional bank / user_id / dataset scope
limitNoMax hits where the provider supports it
queryYesSearch query text

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.0
    • changedInput schema / properties / bank / description
      Previous value: -"Optional bank / user_id scope"New value: +"Optional bank / user_id / dataset scope"
    • changedInput schema / properties / limit / description
      Previous value: -"Max results where supported"New value: +"Max hits where the provider supports it"
    • addedInput schema / properties / query / description
      Added value: +"Search query text"
  2. First observedv0.6.3

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare the operation as read-only, idempotent, non-destructive, and open-world. The description adds that results are raw ranked hits rather than synthesized answers, which is useful behavioral context, but it does not explain ranking behavior, pagination, or provider-dependent limits.

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 short sentences, front-loaded with what the tool returns and followed by routing guidance. Every sentence adds value and there is no redundant restatement.

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 search tool with no output schema, the description minimally indicates the return type (ranked raw hits), but it does not describe result structure, ranking semantics, or how the limit parameter behaves when the provider supports it. It is adequate but leaves meaningful gaps.

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 100%, so the schema already documents query, bank, and limit. The description adds no parameter-specific syntax or constraints beyond what the schema provides, making baseline 3 appropriate.

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?

The description states a specific verb and resource ("Return ranked raw hits from stored memories") and distinguishes the tool from memory_recall and memory_reflect by contrasting raw hits with question answering and synthesis. An agent can tell what this tool returns without opening sibling schemas.

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?

It names two alternatives (memory_recall for questions, memory_reflect for synthesized answers), which gives clear routing guidance. It does not explicitly state exclusions or edge cases, but the intended use is strongly implied.

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