Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Apuntar una decisión

record_decision

Apunta una decisión del proyecto con su porqué. Solo las que se podrían reabrir dentro de meses o que cuesta revertir. Sin porqué no se guarda.

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": {
      "project": "<project>",
      "text": "<text>",
      "why": "<why>"
    },
    "name": "record_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
whyYesPor qué, con sus palabras.
textYesQué se decidió.
sourceNoEl transcript o la conversación de la que sale, si tiene id o título estable.
projectYesEl proyecto (p1, p2…), de list_projects.
assumptionsNoQué tiene que seguir siendo cierto para que valga. Solo si lo ha dicho él; no lo deduzcas.
occurred_onNoCuándo pasó, AAAA-MM-DD, solo si lo dice él o la fuente. Si cuenta algo de hoy sin dar fecha, déjalo vacío: no pongas hoy.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare this is a non-read, non-destructive, non-idempotent write, so the safety profile is covered. The description adds one behavioral rule, that records without a 'why' are not saved, but it says nothing about duplicate handling despite idempotentHint=false, nor about what is returned or whether entries can be edited later.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: what it records, what qualifies, and the hard precondition. Nothing is repeated and the qualification rule is front-loaded before the constraint.

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?

Six params with full schema documentation and annotations covering the safety profile leave little for the description to carry. The two things an agent most needs from prose, the inclusion bar and the mandatory rationale, are both stated.

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%, and the schema already carries nuanced guidance for source, assumptions and occurred_on. The description only restates that 'why' is mandatory, adding no format, vocabulary or precedence detail beyond the structured fields.

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 states a concrete verb and resource: 'Apunta una decisión del proyecto con su porqué'. An agent knows it is capturing a project decision plus its rationale, which is distinct from siblings like add_learning or add_gotcha by content type, though those siblings are never named as boundaries.

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?

It gives an explicit inclusion filter: only decisions that could be reopened months later or are costly to revert, plus a hard precondition ('Sin porqué no se guarda'). It does not name an alternative tool for the excluded cases, so routing is implied rather than spelled out.

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