Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Añadir lo tuyo a una nota

extend_note

Guarda en una nota lo que el usuario piensa de ella (su acuerdo, su desacuerdo, cómo lo aplica, en qué caso suyo lo ha visto) o, en una referencia visual, qué le gusta de ella. Copia SUS palabras, sin resumir ni mejorar: es su voz pegada a la del autor. Úsala cuando reaccione a una nota que acabas de citar, en el careo de open-brain-extract y cuando brain_health saque referencias sin su «qué me gusta». Se añade con fecha y no borra lo anterior.

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": {
      "id": "<id>",
      "text": "<text>"
    },
    "name": "extend_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesLa nota (n12).
textYesLo que ha dicho el usuario, literal.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (non-read-only, non-destructive, non-idempotent), and the description adds real context on top: it appends with a date and preserves prior content, and the stored text must be the user's verbatim words ('sin resumir ni mejorar'). That verbatim constraint is behavioral guidance an agent could not infer from the schema or annotations.

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?

Purpose is front-loaded and each sentence carries information: what to store, fidelity rules, trigger conditions, and mutation semantics. It runs long and mixes several clauses, but no sentence 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 two-parameter append tool with annotations covering the safety profile and no output schema, the description covers what is stored, fidelity requirements, triggers, and that nothing is overwritten. Remaining gap is only the lack of explicit sibling differentiation.

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 coverage is 100%, so the note id and the literal text are already documented. The description reinforces that text must be unsummarized user voice, adding a little meaning, but the schema's 'Lo que ha dicho el usuario, literal' already says essentially the same. Baseline 3 is appropriate.

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?

States a specific verb and resource: it saves into a note what the user thinks of it (agreement, disagreement, application, personal instance), or for a visual reference, what they like. The appended-not-overwritten behavior ('Se añade con fecha y no borra lo anterior') implicitly separates it from keep_note, though no sibling is named directly. The reference to 'open-brain-extract' names a tool that does not appear in the sibling list, which slightly muddies the routing.

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 three concrete trigger conditions: when the user reacts to a note just cited, during the open-brain-extract careo, and when brain_health surfaces references without the user's 'what I like'. That is explicit when-to-use guidance. The gap is no explicit when-NOT-to-use or direct contrast with keep_note/check_text.

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