Skip to main content
Glama

get_playbook

Read-onlyIdempotent

Las recetas para las preguntas típicas: con qué tools se contestan, en qué orden y cómo entregar. Sin skill: la lista (nombre, para qué, argumentos). Con skill y sus argumentos: la receta armada, para seguirla.

Hay recetas para estas preguntas: investigar una persona, proyecto u
organización; dónde o cuándo se habló de algo; seguimiento de un tema; qué se decidió; preparar o
resumir una reunión; accionables sin confirmar; estado de tareas o de un tablero; tareas de Jira o
ClickUp; lo delegado; el día o la semana; ponerse al día después de unos días; qué está en riesgo;
cómo se relacionan dos cosas; redactar un seguimiento; estudiar un tema; pasar notas a tareas;
ordenar el Atlas.
Y para HACER: armar el Secondbrain de una cuenta nueva, anotar en el diario, recordarme algo, crear una tarea, agendar, completar tareas,
registrar una reunión no grabada, cerrar el día, planificar la semana, ordenar vencidas, armar
un entregable, escribir o actualizar un documento, armar un tablero visual, actualizar el Atlas.

Para una pregunta suelta ("¿en qué quedó X?") no hace falta receta: recall alcanza.

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": "get_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoArgumentos de la receta, ej. { persona: 'Pablo' }
skillNoNombre de la receta (de la lista). Omitir para listarlas

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is covered and the description is not obligated to restate it. Beyond that, the description adds real behavioral context: the response shape differs by invocation mode (catalog vs. assembled recipe meant to be followed), and the recipe is described as instructions for a subsequent multi-tool sequence, which is meaningful. What it omits is failure behavior — what happens if `skill` names an unknown recipe.

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

Conciseness3/5

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

The first two lines are well front-loaded and carry the essential contract. The two long enumerations of recipe topics, however, largely restate what the tool itself returns when called without `skill`, so a substantial share of the text is redundant for an agent that can simply ask for the list. Efficient core, padded middle.

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 must carry the return-value burden, and it does: it specifies the list form (name, purpose, arguments) and the recipe form. Combined with the explicit alternative (`recall`) and the mode explanation, an agent has everything needed to invoke this correctly on the first try; only unknown-skill error behavior is unaddressed.

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 would be 3, but the description adds meaning the schema does not: it makes explicit that omitting `skill` returns the catalog and that combining `skill` with `args` yields an already-assembled recipe to follow, i.e. the args are substituted into the recipe rather than merely passed along. That coupling between the two optional parameters is the key semantic.

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 line states a concrete verb and resource: it returns "recetas" (recipes) that map typical questions to which tools to use, in what order, and how to deliver the answer. It also draws the two operating modes sharply (without `skill` = list; with `skill` + args = assembled recipe), and names the sibling `recall` as the thing it is not, so an agent can distinguish it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicit when-to-use coverage is enumerated by question type (research a person, what was decided, Jira/ClickUp tasks, etc.) and by action type (create a task, close the day, plan the week). It also gives an explicit when-not rule: a one-off question like "¿en qué quedó X?" needs no recipe because `recall` suffices. That is the full when/when-not/alternative triad.

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