Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Apuntar un aprendizaje

add_learning

Apunta una lección del proyecto que sirve fuera de él. Es lo que el usuario se puede llevar a su cerebro personal. Si solo vale para este proyecto, es una gotcha.

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>"
    },
    "name": "add_learning"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesLa lección, que se entienda fuera del proyecto.
basisNomedido solo si hay datos detrás; lo que alguien cuenta es contado.
sourceNoEl transcript o la conversación de la que sale, si tiene id o título estable.
projectYesEl proyecto (p1, p2…), de list_projects.
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

A4.2/5.0
Behavior3/5

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

Annotations already declare this as a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds conceptual context ('es lo que el usuario se puede llevar a su cerebro personal') that hints at downstream reuse, but says nothing about validation, duplicate handling, or what a rejected lesson looks like, which matters for a non-idempotent write.

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 short sentences with zero padding; the positive criterion comes first and the exclusion/alternative immediately after. Every sentence earns its place.

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?

Five parameters with full schema coverage and no output schema, so the description only needs to carry the conceptual boundary, which it does well. It could briefly say what happens to the learning after capture (where it lands, whether it is deduplicated), but nothing essential for correct invocation is missing.

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 parameter including the basis enum and the occurred_on date rule is already documented. The description's generalization requirement for the lesson duplicates what the 'text' schema field already states, adding no new meaning beyond the schema.

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 ('Apunta') and resource ('una lección del proyecto') and immediately states the defining scope condition: the lesson must be useful outside the project. It also names the sibling it is not, distinguishing itself from gotchas in the same breath.

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 an explicit selection rule: if the lesson generalizes beyond the project, use this tool; if it only holds for this project, it belongs in add_gotcha. That is a concrete when-not plus a named alternative, which is exactly what an agent needs to route correctly.

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