Skip to main content
Glama

Extract memories from interactions

extract_memories

Scan recent interactions for memory-intent phrases and propose memory candidates; dry-run by default, pass apply=true to create them.

Instructions

Scan recent captured interactions for memory-intent phrases and propose memory candidates (deterministic, no LLM). Dry-run by default; pass apply=true to create them (source=captured).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "extract_memories"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoInteraction kind to scan (default prompt)
applyNoCreate the proposed memories (default false = propose only)
limitNoMax recent interactions to scan (default 50)
userIdNoScope extracted memories to a user (USER scope)
sessionIdNoFilter by captured session id (default: all sessions)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.4.2
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed1 schema field changedv2.4.0
    • addedInput schema / properties / sessionId
      Added value: +{
      +  "description": "Filter by captured session id (default: all sessions)",
      +  "maxLength": 200,
      +  "type": "string"
      +}
  3. First observedv2.2.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations provided, the description carries the behavioral burden and does well: it discloses determinism, dry-run default behavior, the mutation triggered by apply=true, and the source tag (source=captured). It does not cover authorization, rate limits, duplicate handling, or what the proposed candidates look like.

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?

The description is two sentences, front-loaded with the core action, and contains no filler. Every clause adds useful information about determinism, default mode, or the apply toggle.

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

Completeness4/5

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

For a five-parameter tool with no annotations and no output schema, the description is largely complete on purpose and mutation behavior. It does not describe the shape of proposed memory candidates or return behavior, but it covers what an agent needs to choose dry-run versus apply.

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 all five parameters including defaults and constraints. The description adds meaning only for apply=true, which is already described in the schema, and does not add further parameter semantics beyond that baseline.

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: scan recent captured interactions for memory-intent phrases and propose memory candidates. The phrase 'deterministic, no LLM' adds a useful distinguishing trait. It does not explicitly distinguish itself from siblings like remember or consolidate, so it falls short of a 5.

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 description gives clear operational guidance for dry-run versus apply: 'Dry-run by default; pass apply=true to create them.' However, it does not explain when to use this tool instead of alternatives such as remember, save_lesson, or consolidate, nor does it state prerequisites.

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