Skip to main content
Glama

Gerar dossiê em rascunho (HTML)

gerar_dossie

Generates a reviewable draft HTML dossier with summary, deadline, checklist, used or discarded evidence, and required fixes, returning the file path and rule checklist; it does not send the dossier.

Instructions

Roda conferir_provas de novo e gera o dossiê em RASCUNHO saida/dossie-.html (resumo, prazo, checklist, provas usadas, provas descartadas e por quê, o que corrigir, e o que foi extraído de cada imagem). NÃO envia nada: o produtor revisa e envia por conta própria. Retorna o caminho do arquivo e o checklist das regras (veredito, Atenção, o que corrigir) — repasse esses motivos ao produtor como retornados.

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": {
      "contestacao_id": "<contestacao_id>",
      "provas_extraidas": "<provas_extraidas>"
    },
    "name": "gerar_dossie"
  }
}

Input Schema

NameRequiredDescriptionDefault
contestacao_idYesID da contestação, ex.: CB-002
provas_extraidasYesUm item por documento lido em buscar_documentos, com o que foi extraído de cada imagem

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses a write side effect (a file created at saida/dossie-<id>.html), an implicit side effect (re-running conferir_provas), and an explicit non-action (nothing is sent). It also describes the return payload. It omits whether an existing file at that path is overwritten and whether any permission or contestação state is required.

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?

Three front-loaded sentences: purpose and output path first, then the safety boundary, then the return value. The parenthetical section list is long but each item describes real file content, so it earns its place; the prose is slightly run-on but there is no 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?

There is no output schema, and the description compensates by naming what is returned (file path plus the rules checklist with verdict, Atenção and what to fix). Given the tool re-runs another tool and writes a file, it is nearly complete; only overwrite/collision behavior remains unstated.

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 both parameters are documented in detail in the schema itself (including the nested provas_extraidas fields), so a baseline of 3 applies. The description only indirectly alludes to provas_extraidas through the mentioned 'provas usadas / provas descartadas' sections, adding no format or constraint detail 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 artifact: it re-runs conferir_provas and produces the dossier as a DRAFT at saida/dossie-<id>.html, then lists the exact sections the file contains. This distinguishes it from conferir_provas (validation only) and the other read-only siblings without the agent needing to open 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It makes explicit when this tool is the right choice: when a reviewable dossier artifact is needed, since it re-runs conferir_provas itself. It also states the critical boundary (it does NOT send; the producer reviews and sends) and instructs the agent to relay the returned reasons to the producer. It stops short of stating prerequisites, such as whether conferir_provas must have passed first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.