Skip to main content
Glama

recall

Read-only

Search memory by keywords or meaning to retrieve matching facts or episodes that are true now, or as of a given date.

Instructions

Busca en la memoria por palabras y por significado.

    Por defecto solo devuelve lo que es verdad ahora. Siempre devuelve los resultados más
    cercanos, aunque estén poco relacionados: juzga tú si responden a la pregunta.
    

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": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoNúmero máximo de resultados.
kindNoSolo fact o solo episode.
as_ofNoResponder con lo que era verdad en esta fecha (ISO 8601).
queryYesQué buscar, en lenguaje natural.
include_historyNoIncluir también las versiones reemplazadas.

Output Schema

NameRequiredDescriptionDefault
modeYes"vector" (significado), "hybrid" (significado + palabras) o "fts_only" (solo palabras)
resultsYes
warningsNo

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?

Beyond readOnlyHint/openWorldHint, it discloses two non-obvious behaviors: the default filters to currently-true memory, and there is no relevance threshold, so weakly related hits are still returned. Both materially change how an agent should interpret output. It does not describe ordering specifics or failure modes, but the annotations and output schema cover part of that burden.

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?

Three short sentences, front-loaded with purpose before the temporal caveat and the relevance warning. Nothing is redundant; the closing 'juzga tú si responden a la pregunta' is an actionable instruction rather than filler.

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 read-only search tool with a full output schema and 100% parameter documentation, the description supplies the remaining semantics an agent needs: default temporal filtering and unfiltered nearest-neighbor results. Missing only explicit sibling routing/relationship to history, which would push it to a 5.

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 coverage is 100% and each parameter is already documented (k, kind, as_of, include_history, query). The description only adds the default temporal behavior, which loosely contextualizes as_of and include_history but does not clarify their syntax or interaction. Baseline 3 applies since the schema carries the weight.

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?

States a concrete verb and resource ('Busca en la memoria') plus the retrieval mechanism ('por palabras y por significado'), which is specific enough for an agent to know this is a search tool rather than a listing one. It never names a sibling such as list_memories or history, so differentiation is inferred from behavior rather than stated.

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?

Explains the default temporal scope ('solo devuelve lo que es verdad ahora') and warns that results are always returned ranked-nearest, so the agent must judge relevance itself. That is useful operational guidance, but there is no explicit 'use this instead of X when...' routing against siblings like list_memories or history.

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

Deploy Server

Other Tools