Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Archivar un proyecto

archive_project
Idempotent

Archiva un proyecto, o todos los de una empresa cuando el usuario la deja. No borra nada: el proyecto deja de salir en las listas y en get_context, no se puede apuntar en él y solo se abre si el usuario lo pide, con un aviso de que es de un proyecto pasado y puede tener datos privados. Devuelve sus aprendizajes: ofrécele llevarse a su cerebro los que quiera, contados sin nombres de la empresa, sus clientes ni sus compañeros. Con restore vuelve a estar activo.

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": "archive_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoEl proyecto (p1, p2…).
reasonNoPor qué se archiva, en una frase (p. ej. «dejé la empresa»).
companyNoLa empresa: archiva todos sus proyectos.
restoreNoSacarlo del archivo. Solo si el usuario lo pide.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare non-destructive, idempotent mutation; the description adds real behavioral context beyond that: nothing is deleted, the project vanishes from lists and get_context, cannot be pointed at, and only opens with a privacy warning. It also discloses the return payload (learnings, counted without company/client/coworker names) and the follow-up action of offering to move them to the brain.

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 core action and its non-destructive nature are front-loaded, and every clause carries information (scope, visibility, privacy warning, returned learnings). It is a dense multi-clause paragraph, so slightly harder to scan, but nothing is filler.

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?

For a mutation tool with no output schema, the description covers the side effects, the restore path, and the shape of what is returned (anonymized learnings plus an offer to save them). An agent has everything needed to call it and to explain the consequences to the user.

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 adds meaning beyond the field labels: company archives all of that company's projects, and restore reactivates the project only on explicit user request. That clarifies the interaction between the id, company and restore parameters.

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?

States a specific verb and resource ("Archiva un proyecto") plus a scope variant (all projects of a company when the user leaves). It also names the inverse operation ("Con restore vuelve a estar activo"), so an agent can distinguish it from update_project or list_projects without opening a schema.

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?

Gives concrete triggering contexts: archiving one project, or all projects when the user leaves the company, and the restore condition "Solo si el usuario lo pide". It does not explicitly contrast with update_project, but the when-to-use guidance is clear enough to act on.

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

All MemoryBrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources