Conector Juspronto

Autos: buscar no tribunal

autos_tribunal

Idempotent

Pede ao Robô JusPronto as peças públicas do processo inteiro (acao buscar; atualizar faz o mesmo pedido). A prévia mostra o custo do processo inteiro; confirme com os mesmos argumentos e o confirmacaoToken. O mesmo processo só pode ser pedido de novo depois de 24 horas. As peças chegam na aba Documentos em 1 a 5 minutos; depois use listar_pecas com fonte juspronto e ler_paginas com pecaId. Peças sigilosas não vêm por aqui: o advogado envia o PDF. acao baixar, com a key de listar_pecas, devolve uma peça que já está salva nos documentos do processo. processo_status e listar_pecas não baixam peça nem cobram por documento.

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": {
      "acao": "<acao>",
      "processoId": "<processoId>"
    },
    "name": "autos_tribunal"
  }
}

Input Schema

Name	Required	Description
`key`	No	Chave opaca de uma peça já salva, obtida em listar_pecas; nunca exibir ao advogado
`acao`	Yes	buscar = pedir ao Robô JusPronto as peças públicas do processo inteiro, com prévia de custo; atualizar = o mesmo pedido de buscar; baixar = devolver uma peça que já está salva nos documentos do processo (key de listar_pecas)
`titulo`	No
`extensao`	No
`processoId`	Yes
`confirmacaoToken`	No	Só depois de mostrar a prévia e o advogado confirmar; repetir os mesmos argumentos

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 2, 2026

changedInput schema / properties / acao / description

Previous value: -"buscar = Buscar autos no tribunal; baixar = uma peça da lista; atualizar = comparar IDs do PJe e baixar só os documentos que faltam, com prévia de custo"New value: +"buscar = pedir ao Robô JusPronto as peças públicas do processo inteiro, com prévia de custo; atualizar = o mesmo pedido de buscar; baixar = devolver uma peça que já está salva nos documentos do processo (key de listar_pecas)"

changedInput schema / properties / key / description

Previous value: -"Chave opaca obtida em listar_pecas com fonte tribunal; nunca exibir ao advogado"New value: +"Chave opaca de uma peça já salva, obtida em listar_pecas; nunca exibir ao advogado"

Changed2 schema fields changedOct 26, 2026

changedInput schema / properties / acao / description

Previous value: -"buscar = mesmo botão Buscar autos no tribunal; baixar = UMA peça da lista do tribunal"New value: +"buscar = Buscar autos no tribunal; baixar = uma peça da lista; atualizar = comparar IDs do PJe e baixar só os documentos que faltam, com prévia de custo"

changedInput schema / properties / acao / enum

Previous value: -[
-  "buscar",
-  "baixar"
-]New value: +[
+  "buscar",
+  "baixar",
+  "atualizar"
+]

AddedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations, it discloses the cost preview, the confirmation-token requirement, the asynchronous delivery window with where results land (aba Documentos), the 24-hour cooldown, and the confidential-piece exception. One nuance is that idempotentHint=true sits slightly awkwardly with a rule that a repeat request is refused for 24 hours, but the description's added context is otherwise substantial.

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 core request is front-loaded in the first sentence and every subsequent sentence adds operational information rather than filler. It is a dense run-on paragraph, though, and a bulleted split of the actions would make 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?

For a six-parameter mutation tool with no output schema, the description covers the full lifecycle: request, cost preview, confirmation, delivery latency, where the artifacts appear, and which sibling tools continue the workflow. An agent could invoke and follow up correctly without any further documentation.

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

Parameters4/5

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

With 50% schema coverage, the description carries real weight: it defines all three acao values behaviorally, explains that baixar needs the opaque key from listar_pecas, and clarifies that confirmacaoToken must be sent with the same arguments as the preview. It adds nothing for titulo, extensao, or processoId, which remain undocumented in both schema and description.

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 opens with a specific verb and resource ('Pede ao Robô JusPronto as peças públicas do processo inteiro') and immediately distinguishes the three actions, noting that 'atualizar faz o mesmo pedido' and that 'baixar' returns an already-saved piece. It also names the sibling tools (listar_pecas, ler_paginas, processo_status) an agent would otherwise confuse it with.

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?

It spells out the two-step flow (preview cost, then confirm with the same arguments plus confirmacaoToken), the 24-hour re-request limit, and the follow-up path (wait 1-5 minutes, then listar_pecas with fonte juspronto and ler_paginas with pecaId). It explicitly states what this tool does NOT do ('Peças sigilosas não vêm por aqui: o advogado envia o PDF', and processo_status/listar_pecas neither download nor charge), which is exactly the routing guidance an agent needs.

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

All Conector Juspronto tools Inspect

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

Need Help?