Skip to main content
Glama

recall

Read-onlyIdempotent

Contesta una pregunta con todo lo que el workspace sabe, en una sola llamada:

  pasajes    los fragmentos más relevantes de documentos, recaps, notas del diario,
             tareas, informes y archivos — búsqueda por SIGNIFICADO (embeddings) +
             TEXTO, así que encuentra aunque la pregunta no use las mismas palabras.
             Trae el TEXTO del fragmento, no un snippet: casi siempre alcanza para
             responder sin abrir nada.
  entidades  las personas / proyectos / organizaciones en juego (las que nombra la
             pregunta y las que dominan los pasajes). De cada una: su artículo del
             WIKI del Atlas (qué es, historia, estado actual, gente), sus tareas
             ABIERTAS y dónde apareció último.
  tareas     las que salieron en la búsqueda, con el estado REAL de hoy.

Sin workspace_id (y con sesión de usuario) pregunta en TODOS sus workspaces a la vez.
Cada resultado trae en `abrir` la tool exacta para ver la fuente entera.

Preguntas de ejemplo: "¿en qué quedó lo de Visa?", "¿qué dijo Pablo sobre la conciliación?",
"decisiones de arquitectura del producto", "¿qué tengo pendiente con Banorte?".

profundidad: rapida (resúmenes, ~6 pasajes) · normal (default) · profunda (20 pasajes,
wikis enteros — para informes o preguntas amplias).

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": {
      "question": "<question>"
    },
    "name": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
desdeNoYYYY-MM-DD: sólo material desde esa fecha
hastaNoYYYY-MM-DD: sólo material hasta esa fecha
questionYesLa pregunta, en lenguaje natural, tal como la haría el usuario
profundidadNoCuánto contexto traer (default: normal)
workspace_idNoUUID o nombre del workspace ('Acme', 'el personal'). Omitir para preguntar en todos los del usuario

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered, yet the description adds substantial behavior the annotations cannot convey: cross-workspace fan-out when workspace_id is omitted, full fragment text rather than snippets, hybrid semantic+text matching, and the presence of an `abrir` pointer in each result. These are exactly the details an agent needs to decide it does not have to call a follow-up tool.

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?

The definition is front-loaded with the core promise, then a labeled breakdown of return sections, then the cross-workspace caveat and the profundidad dial. It is longer than minimal and leans on heavy capitalization for emphasis, but no sentence is pure filler; the aligned block format makes it scannable.

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

Completeness5/5

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

There is no output schema, so the description carries the full burden of describing returns and does so in detail: what each of the three sections contains, how entities surface (named in the question, or dominant in passages), and that results carry an `abrir` handle to the underlying tool. For a multi-workspace read tool with 5 params, nothing an agent needs before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning for `profundidad` by quantifying the tiers (~6 pasajes for rapida, 20 pasajes plus wikis enteros for profunda), which the schema only labels as 'Cuánto contexto traer'. It also restates and clarifies the workspace_id omission behavior, though desde/hasta get no elaboration beyond the schema.

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 opening sentence states a specific verb and scope: 'Contesta una pregunta con todo lo que el workspace sabe, en una sola llamada'. It then breaks the response into three named blocks (pasajes, entidades, tareas) and explains how each is sourced (embeddings + texto, wiki del Atlas, estado real de tareas), which is far more than a restatement of the name 'recall'.

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 provides concrete triggering examples ('¿en qué quedó lo de Visa?', '¿qué tengo pendiente con Banorte?') and rules for choosing profundidad (rapida for resúmenes, profunda for informes o preguntas amplias), plus the workspace_id omission rule. What it lacks is an explicit when-not-to-use or a named alternative; the routing is only implicit via 'Cada resultado trae en `abrir` la tool exacta para ver la fuente entera'.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources