Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Guardar una skill tuya

save_skill
Idempotent

Guarda o actualiza una skill del usuario en su cerebro: el procedimiento que seguirás tú cuando la cargue con get_skill. Cada cambio sube la versión. Solo la ve él hasta que la comparta (share_skill). Úsala cuando quiera convertir en skill cómo hace algo («guárdalo como skill», «quiero que mis alumnos practiquen así»). Redacta el procedimiento con él y enséñaselo antes de guardar. La tarjeta es una de las del servidor (ninguna, pronunciacion, proyecto); para pronunciación, card: { kind: "pronunciacion", phrases: [{ topic, text }] } y luego él graba la referencia de cada frase con show_pronunciation y skill. tools: las tools de este servidor que usa. Una skill no puede compartir, conectar, borrar, exportar ni mandar nada fuera, ni nombrarlo en su texto. Si adapta otra, based_on dice cuál.

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": {
      "name": "<name>"
    },
    "name": "save_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardNoLa tarjeta: «ninguna», «proyecto» o { kind: "pronunciacion", phrases: [{ topic, text }] }.
nameYesNombre corto en minúsculas con guiones (pronunciacion-ingles). Con uno que ya tiene, la actualiza.
toolsNoLas tools del servidor que usa (p. ej. add_gotcha, add_learning, show_pronunciation).
based_onNoSi adapta otra skill, cuál y de quién (p. ej. «practicar-idiomas, de Carlos Moya»).
procedureNoEl texto de la skill: los pasos, el criterio y qué apuntar en el proyecto.
descriptionNoQué hace y cuándo se carga, en una o dos frases.

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-read-only, idempotent, non-destructive. The description adds real behavior the annotations cannot: every change bumps the version, the skill stays private to the user until shared, and a skill may not share, connect, delete, export, or send anything outside nor even name such actions in its text — a hard content constraint an agent must know.

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?

One dense paragraph, front-loaded with the action and the visibility/versioning traits, then triggers, then constraints. Every sentence carries information, though the constraint sentence is long and the card/pronunciation instructions could be broken out for faster scanning.

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 6-parameter mutation tool with no output schema, the description covers purpose, triggers, versioning, privacy, hard content limits, card variants, and the tools/based_on semantics — enough to call it correctly without opening the schema.

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 baseline is 3, but the description adds meaning beyond the schema: it explains the pronunciation card flow end-to-end (card shape, then the user records each phrase reference via show_pronunciation) and clarifies that `tools` means tools of this server. It restates some schema text (name format, based_on) but the workflow detail is genuinely additive.

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 ('Guarda o actualiza una skill del usuario en su cerebro') and immediately explains what a skill is ('el procedimiento que seguirás tú cuando la cargue con get_skill'), which distinguishes it from get_skill and share_skill.

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 trigger phrases ('guárdalo como skill', 'quiero que mis alumnos practiquen así') plus a workflow instruction to draft the procedure with the user before saving, and points to share_skill for the sharing case. It stops short of stating when NOT to use it or naming sibling save_* tools as alternatives, so it is strong but not exhaustive.

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