Skip to main content
Glama

memory_recall

Read-only

Retrieves active, approved memories—such as durable preferences, identity facts, and project decisions—so agents can reuse prior context instead of asking again.

Instructions

Recall active approved Lucy memory only. Use for durable preferences, identity, project decisions, or explicit remember/recall. Do not use for arithmetic, weather, news, or one-shot drafting.

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>",
      "scope": "<scope>"
    },
    "name": "memory_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysNo
kindsNo
limitNo
queryYes
scopeYes

Output Schema

NameRequiredDescriptionDefault
as_ofYes
scopeYes
noticesYes
resultsYes
request_idYes
consistencyYes
schema_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds meaningful semantics beyond that: results are restricted to "active approved" memories, implying revoked, superseded, forgotten, or unapproved entries are never returned even though the schema exposes those lifecycle values elsewhere. It doesn't disclose ranking, match threshold, or how results are ordered when limit is hit.

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: capability first, then when to use, then when not to use. No redundancy with the title, no filler, and the most decision-relevant constraint (approved/active only) is front-loaded.

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 shape needn't be explained, and annotations cover the read-only safety profile. However, with 0% schema description coverage on five parameters, the definition is incomplete for an agent that must choose between query, keys, and kinds filters or pick a scope. It is adequate to decide whether to call the tool but not fully adequate to call it well.

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 0% across five parameters, so the description carries the full explanatory burden and does not meet it. Nothing is said about what query matches against, what the keys filter does versus free-text query, how kinds narrow results, which scope values are valid, or what limit (default 3, max 5) controls. Only the implicit notion of "Lucy memory" hints at data domain, leaving the agent to infer the rest from JSON Schema patterns alone.

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 opens with a specific verb and resource ("Recall active approved Lucy memory") and constrains scope to active, approved memories. It doesn't explicitly contrast itself with the sibling memory_propose or memory_proposal_status tools, but the verb/resource pairing is distinct enough to separate reads from proposals.

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 gives concrete positive triggers (durable preferences, identity, project decisions, explicit remember/recall requests) and an explicit exclusion list (arithmetic, weather, news, one-shot drafting), which is unusually strong routing guidance. It stops short of a 5 because it never names the alternative memory tools an agent should switch to for write or status operations.

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