Conector Juspronto

Consultar saúde das integrações

saude_integracoes

Read-only

Mostra se DJEN, tribunal e robô de andamentos, certificado, WhatsApp, e-mail ou Judit estão funcionando. Informe integracao; processoId é opcional; periodo recebe inicio e fim ISO 8601, padrão últimos 30 dias, máximo 366. O estado é o pior entre os registros do período, inclusive monitor ou varredura do DJEN sem resposta há dias. Mostra última execução comprovada, falha categorizada, próximo passo, custo e limite quando houver e link seguro para a tela. Distingue enviado ao provedor de entregue. WhatsApp exige gestão; e-mail mostra somente envios ao usuário da conexão. DJEN por pasta informa ausência de vínculo, sem ampliar a consulta ao escritório. Certificados mostram só validade e titular por iniciais. Lista os 20 primeiros certificados, diz quantos faltam e conta todos os vencidos; o período filtra a execução. Autenticação acontece somente na tela do JusPronto. Não executa trabalho, não chama provedores nem altera configurações.

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": {
      "integracao": "<integracao>"
    },
    "name": "saude_integracoes"
  }
}

Input Schema

Name	Required	Description	Default
`periodo`	No
`integracao`	Yes
`processoId`	No

Output Schema

Name	Required	Description	Default
`link`	No
`aviso`	No
`custo`	No
`falha`	No
`escopo`	No
`estado`	No
`limite`	No
`resumo`	No
`entrega`	No
`periodo`	No
`truncado`	No
`restantes`	No
`integracao`	No
`certificados`	No
`proximoPasso`	No
`avisoConteudo`	No
`ultimaExecucao`	No
`totalCertificados`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well past the annotations (which only declare read-only/non-destructive/closed-world): it explains aggregation semantics ('O estado é o pior entre os registros do período'), output rows ('última execução comprovada, falha categorizada, próximo passo, custo e limite'), a subtle distinction ('Distingue enviado ao provedor de entregue'), visibility restrictions for WhatsApp/e-mail/DJEN-per-folder/certificates, and pagination limits (20 certificates, counts remaining and all expired). These are exactly the behavioral facts an agent cannot infer from schema or annotations.

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?

Purpose is front-loaded in the first sentence and every later sentence carries a real rule rather than filler. It is nonetheless a dense semicolon-chained block of roughly ten clauses, and the certificate-specific details (holder by initials, 20-item cap, expired count) could be compressed.

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?

For a 3-parameter read-only tool with a nested date object and an output schema (so return shapes needn't be explained here), the description covers defaults, caps, visibility rules, and edge cases like a DJEN monitor with no response for days. The one missing piece an agent would want is the semantic role of processoId.

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?

Schema description coverage is 0%, so the description must carry all parameter meaning, and it largely does: 'integracao' is required, 'processoId é opcional', and 'periodo recebe inicio e fim ISO 8601, padrão últimos 30 dias, máximo 366'. The gap is that it never says what processoId actually scopes (a single process vs. firm-wide), and the enum values are only listed implicitly through the prose enumeration rather than tied to the parameter.

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?

Opens with a specific verb+resource ('Mostra se DJEN, tribunal e robô de andamentos, certificado, WhatsApp, e-mail ou Judit estão funcionando'), enumerating exactly which integrations are covered. No sibling tool in the list reports integration health, so an agent can route here without ambiguity.

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?

Gives clear operational scoping rules: 'Informe integracao', 'processoId é opcional', period defaults to last 30 days with a 366-day cap, and 'Autenticação acontece somente na tela do JusPronto'. It also states what the tool will not do ('Não executa trabalho, não chama provedores nem altera configurações'), but never names a sibling tool or an alternative path, so the when-to-use-vs-alternative axis is only partially covered.

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?