Skip to main content
Glama

Recall context for a question

memory_recall
Read-onlyIdempotent

Retrieve stored context for a natural-language question across Hindsight, mem0, and Cognee memory providers to ground answers and coding tasks.

Instructions

Retrieve stored context for a natural-language question (Hindsight recall; search on mem0 and Cognee).

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_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
bankNoOptional bank / user_id / dataset scope
limitNoMax items where supported
queryYesQuestion or topic to recall context for

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.0
    • addedInput schema / properties / bank / description
      Added value: +"Optional bank / user_id / dataset scope"
    • addedInput schema / properties / limit / description
      Added value: +"Max items where supported"
    • addedInput schema / properties / query / description
      Added value: +"Question or topic to recall context for"
  2. First observedv0.6.3

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds that recall fans out across multiple providers (Hindsight recall; mem0 and Cognee search), which is genuinely useful behavioral context, but it says nothing about how results from different backends are merged, ranked, or truncated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler. The parenthetical is compact but slightly cryptic — 'Hindsight recall' is internal jargon an outside agent cannot decode.

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?

Three parameters with annotations is a modest surface, but there is no output schema, so the description is the only place to explain what recall returns — a merged multi-provider result set, its ordering, or whether empty results are possible. That gap leaves the agent guessing about the return shape.

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 `query`, `bank`, and `limit` are already documented in structured form; baseline 3 applies. The description reinforces that `query` is a question/topic but adds no syntax, scope, or limit semantics beyond 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?

Specific verb+resource: retrieves stored context for a natural-language question, and the parenthetical names the backends involved (Hindsight, mem0, Cognee). It does not, however, distinguish itself from sibling `memory_search` or `memory_pages_search`, leaving ambiguity about which retrieval tool 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for a natural-language question' implies semantic/question-style recall rather than keyword lookup, which is modest guidance. There is no explicit when-to-use vs `memory_search`, no exclusion, and no mention of prerequisites or expected follow-up.

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