Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Comprobar un texto

check_text
Read-onlyIdempotent

Comprueba un texto con los checks automáticos de doc-family antes de entregarlo. mode «write» (doc-write y doc-eval): cifras, fechas y URLs que no salen del material, promesas genéricas, cualificadores apilados, ritmo, cierre, estructura decorativa y caracteres invisibles. mode «improve» (doc-improve): que las cifras, nombres, cualificadores y obligaciones del original sigan, que no entre ninguna relación causal nueva, cuánto ha cambiado y que no crezca. Devuelve PASS, WARN o FAIL por check; no entregues con un FAIL abierto. No guarda nada.

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": {
      "mode": "<mode>",
      "text": "<text>"
    },
    "name": "check_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
textYesEl texto a comprobar (en improve, el editado).
briefNoCon write: el brief o encargo, para comprobar que no se reimprime en el texto.
projectNoSi el texto es de un proyecto con marca (p1, p2…): añade los checks de su marca (palabras que no usa, nombres mal escritos).
markdownNofalse si el texto va a un sitio que no pinta markdown (WhatsApp, un email en texto plano, LinkedIn): entonces los títulos con # son un fallo.
materialNoCon write: el material del que sale (lo que dio el usuario y las notas leídas). Sin él no se comprueban las cifras.
originalNoSolo con improve: el texto original.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Si el texto es de un proyecto con marca (p1, p2…): añade los checks de su marca (palabras que no usa, nombres mal escritos).",
+  "type": "string"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description reinforces this with 'No guarda nada' and adds substantive behavior beyond the annotations by explaining the PASS/WARN/FAIL verdict model and that results are per-check. It does not specify whether checks are exhaustive or how many checks run, leaving a small gap.

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?

It is front-loaded with the purpose and then cleanly splits the write and improve check lists, with the return contract placed last where it belongs. The single long sentence enumerating the write-mode checks is dense but every item carries information, so nothing is wasted.

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?

With no output schema, the description correctly compensates by describing the return values (PASS/WARN/FAIL per check). For a 7-parameter tool with high schema coverage and read-only annotations, this is nearly complete, missing only detail on ordering or how many checks are returned.

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 86%, so the schema already explains text, brief, project, markdown, material and original in detail. The description adds value by grouping which parameters matter per mode (write vs improve) and tying 'material' to the numeric checks, but it does not contribute format or syntax guidance 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?

The description states a specific verb and resource ('Comprueba un texto') and immediately enumerates exactly what is validated in each of the two modes, so an agent knows precisely what the tool does. No sibling tool in the list performs text checking, and the description makes that role unambiguous.

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 clear usage context ('antes de entregarlo') and routes the agent between the two modes by naming which skill each belongs to (doc-write/doc-eval vs doc-improve), plus the hard rule 'no entregues con un FAIL abierto'. It does not state explicit when-not-to-use conditions or name alternatives, which is minor given no sibling overlaps.

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