Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Apuntar lo que ha salido de la conversación

capture

Escritura automática: apunta de una vez las decisiones, aprendizajes y trampas que han salido en la conversación, sin que el usuario lo pida. Llámala tú antes de cerrar la respuesta en la que salgan, una vez, con todo junto. Todo entra como deducido: se verifica solo cuando se usa en un output que él entrega, o cuando él lo confirma. Solo lo que ha pasado o se ha dicho en la conversación, en sus palabras; no inventes ni resumas el chat. Lo que no es de ningún proyecto va a «Personal».

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": {
      "facts": "<facts>"
    },
    "name": "capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
factsYesDe 1 a 8 cosas.
sourceNoLa conversación o el transcript del que sale, si tiene id o título estable: no se apunta dos veces.
projectNoEl proyecto de todo lo que no diga otro (p1…), de list_projects o get_context. Sin él va a «Personal».

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare a non-destructive, non-idempotent, non-open-world write, so the safety bar is covered. The description adds real behavioural context beyond them: everything is stored with a 'deducido' status that only flips on confirmed use or user confirmation, and passing a stable source id prevents double-recording. Error behaviour and what gets returned are not covered.

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?

Front-loaded with the trigger ('Escritura automática') and each sentence carries a distinct rule: when to call, storage status, content fidelity, project fallback. The status sentence is dense and reads run-on, but nothing is padding.

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 3-parameter mutation tool with no output schema, the definition covers trigger, batching, content limits, deduplication, and project fallback, which is nearly everything an agent needs. The only real gap is the return value, which no output schema documents either.

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 description coverage is 100%, so the schema already explains facts, kind, why, avoid, and the project fallback to «Personal». The description adds only fit-and-finish guidance ('en sus palabras', don't summarize the chat) and the all-at-once batching expectation, which is marginal over the schema's maxItems: 8.

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?

The description names a specific verb (apunta) and a specific resource set (decisiones, aprendizajes y trampas) with a clear source (la conversación). 'Una vez, con todo junto' hints that this is the batch path versus per-item siblings like add_learning or add_gotcha, but no sibling is named, so the differentiation stays implicit.

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?

Timing and agency are explicit: call it yourself, before closing the response in which the items appear, once, with everything together, without the user asking. It also bounds content ('solo lo que ha pasado o se ha dicho en la conversación; no inventes') and routing ('lo que no es de ningún proyecto va a «Personal»'). What's missing is an explicit pointer to the alternative single-item tools for agents deciding between them.

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