Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Avisar a Carlos de un fallo o una carencia

report_feedback

Avisa a Carlos (quien mantiene MemoryBrain) de algo de ESTE SERVIDOR que te ha fallado o que te ha faltado mientras trabajabas para el usuario: una tool que devuelve algo distinto de lo que dice, un error que no se explica, un parámetro que no hace nada, o algo que necesitabas y no existe. Llámala tú, sin pedirle permiso al usuario y sin interrumpir lo que estás haciendo: es para el servidor, no para el usuario. Una vez por problema y solo si te ha estorbado de verdad. No metas notas del usuario, nombres ni datos personales: cuenta qué pasó con la tool, no con su contenido. No es para pasarle una conversación (eso es send_handoff) ni para dudas del usuario.

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": {
      "tried": "<tried>",
      "happened": "<happened>"
    },
    "name": "report_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo`problema`: algo existe y falla o devuelve algo inesperado. `capacidad_faltante`: necesitabas algo que no existe.
toolNoLa tool afectada, p. ej. search_brain. Vacío si es el servidor en general.
reproNoLos argumentos exactos, sin contenido del usuario, para que Carlos lo reproduzca (máx. 800).
triedYesQué intentabas conseguir y con qué llamada (máx. 600).
clientNoDesde dónde hablas: ChatGPT, Claude, Cursor… Si lo sabes.
happenedYesQué pasó en lugar de lo esperado, con el texto del error si lo hay (máx. 600).
workaroundNoCómo lo rodeaste, si lo hiciste (máx. 400).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only say this is a non-readonly, non-destructive, non-idempotent, closed-world call. The description adds real context beyond that: the report goes to the server maintainer and not to the user, calls should be deduplicated per problem, and a hard privacy constraint forbids user notes, names or personal data. It does not say what happens after submission (ticket created? any acknowledgement?), which is the remaining gap for a write tool with no output schema.

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-loads the recipient and the trigger before the operational rules, and each sentence carries a distinct constraint (autonomy, frequency, privacy, exclusions). Slightly long and does repeat the not-for-the-user point twice, but nothing is filler.

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 seven-parameter reporting tool with full schema coverage and no output schema, the description covers purpose, triggers, alternatives, frequency and privacy adequately. The only omission is what the agent gets back or what happens to the report after submission, which matters somewhat given there is no output schema to explain it.

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 every one of the seven fields is already documented, including the kind enum and the length caps on tried/happened/repro. The description reinforces the privacy rule that the repro must carry arguments but no user content, but adds little field-level meaning beyond what the schema already states. Baseline 3 applies.

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?

Names a specific verb and recipient plus the exact class of object reported: a tool of THIS server that failed, returned something different than documented, has a parameter that does nothing, or something missing entirely. It also explicitly distinguishes itself from send_handoff and from user questions, so an agent can route without opening any 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?

Gives explicit when-to-call triggers, an autonomy rule (call it yourself without asking the user, without interrupting the task), a frequency limit (once per problem, only if it actually blocked you), and explicit exclusions (not a conversation handoff, not user doubts). Alternatives are named rather than inferred.

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