Skip to main content
Glama

Conector Juspronto

Abrir e comparar versões da minuta

abrir_minuta
Read-only

Abre uma versão pelo minutaId, com texto integral em páginas de 6 mil caracteres, hashVersao, versões da mesma minuta, conferências determinísticas já calculadas, pendências de fontes, as citações com a verificação automática de cada uma e o histórico de decisão (aprovação, retirada e download do DOCX). pagina, paginaVersoes e paginaFontes continuam o texto, as versões e as referências. compararComId compara duas versões da mesma minuta; paginaDiff continua os trechos removido e adicionado. Só leitura. A aprovação humana é distinta da conferência automática. A exportação em DOCX continua no app. Assinar e protocolar a peça ficam com você, fora do Juspronto.

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": {
      "minutaId": "<minutaId>"
    },
    "name": "abrir_minuta"
  }
}

Input Schema

NameRequiredDescriptionDefault
paginaNo
minutaIdYes
paginaDiffNo
paginaFontesNo
compararComIdNo
paginaVersoesNo

Output Schema

NameRequiredDescriptionDefault
textoNo
versaoNo
frescorNo
versoesNo
minutaIdNo
hashVersaoNo
pendenciasNo
avisoConteudoNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already carry readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description reinforces 'Só leitura' rather than contradicting it. Beyond that it adds genuinely useful context: fixed 6,000-character page chunks, page-continuation semantics, and the distinction between human approval and the automatic citation check, plus what happens outside the tool (DOCX export, signing, filing). It does not discuss rate limits or truncation behavior for very large minutas, so not a 5.

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?

The payload summary is front-loaded and every clause adds information; nothing is filler. It is a single dense run-on paragraph, though, and splitting the parameter-continuation rules from the return-value inventory would have made it easier to scan.

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?

Given six parameters, an output schema already present, and zero schema-level documentation, the description covers what an agent needs: what is returned, how to page each stream, how to enter comparison mode, and where the tool's responsibility ends (export, signing, filing). Nothing essential to calling it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so: minutaId identifies the version, pagina/paginaVersoes/paginaFontes each continue a specific sub-stream (text, versions, references), and compararComId plus paginaDiff define the diff mode and its paging. Every one of the six parameters is given meaning the bare schema (types and defaults only) cannot supply.

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 opens with a specific verb and resource — 'Abre uma versão pelo minutaId' — and enumerates the payload (full text, hashVersao, versions, deterministic conferences, source pendencies, citations, decision history). An agent knows exactly what it gets back. What it does not do is name a sibling (e.g., listar_minutas or preparar_secao_minuta) to contrast the single-version read against listing or drafting, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: the description makes clear that compararComId switches the tool into a two-version diff mode and that pagina* parameters continue a previously retrieved run. It also sets boundaries (DOCX export, signing and filing live elsewhere). But there is no explicit 'use X instead when' routing against the many sibling tools, leaving the agent to infer when this is the right entry point.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources