Skip to main content
Glama

astrea_prazo_criar

Cria um PRAZO processual no Astrea (aparece como prazo na agenda e nos relatórios de prazos, não como tarefa solta), vinculado a um processo ou caso, e opcionalmente as TAREFAS que dependem dele, tudo numa chamada (ex.: prazo fatal 06/11 para protocolar; tarefas "levantar movimentações", "minuta", "revisão").

  • case_id: id do processo ou caso (ver astrea_processos).

  • title: título do prazo (até 250 caracteres).

  • Data fatal, de UM destes dois jeitos: a) due_date: a data fatal pronta, AAAA-MM-DD; ou b) dias + data_inicial (+ contagem): o ASTREA calcula a data fatal. data_inicial = data da intimação/publicação de onde a contagem parte; contagem "uteis" (padrão: o Astrea pula fins de semana, os feriados do calendário dele e o recesso forense cadastrado; considerar_recesso=false ignora o recesso) ou "corridos" (soma N dias de calendário, sem prorrogar fim de semana, igual à tela do Astrea). A resposta traz a data calculada e os feriados/recesso considerados: confira com o usuário antes de confiar, o próprio Astrea recomenda checar a data no tribunal.

  • responsible_id: opcional, responsável pelo prazo (ver astrea_responsaveis); se omitir, fica no usuário da integração e pode não aparecer na agenda do advogado.

  • comments: opcional, observações do prazo. tag_ids: opcional, etiquetas (ver astrea_etiquetas; a etiqueta precisa permitir prazos).

  • tarefas: opcional, tarefas vinculadas ao prazo. Cada uma com description e a data: due_date (AAAA-MM-DD) OU dias_antes (dias corridos antes da data fatal; omitindo os dois, vence na data fatal). responsible_id por tarefa (ex.: estagiária numa, advogada noutra). Devolve prazo_id (editar com astrea_prazo_editar, cancelar com astrea_prazo_cancelar, excluir com astrea_prazo_excluir) e, por tarefa, task_id. Falha numa tarefa não desfaz o prazo: veja "tarefas[].criada" e crie só a que faltou com astrea_tarefa_criar + prazo_id.

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": {
      "case_id": "<case_id>",
      "title": "<title>"
    },
    "name": "astrea_prazo_criar"
  }
}

Input Schema

NameRequiredDescriptionDefault
diasNo
titleYes
case_idYes
tag_idsNo
tarefasNo
commentsNo
contagemNo
due_dateNo
data_inicialNo
responsible_idNo
considerar_recessoNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / considerar_recesso
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / contagem
      Added value: +{
      +  "enum": [
      +    "uteis",
      +    "corridos"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / data_inicial
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / dias
      Added value: +{
      +  "type": "number"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "case_id",
      -  "title",
      -  "due_date"
      -]New value: +[
      +  "case_id",
      +  "title"
      +]
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Well beyond the annotations, it discloses the partial-failure model ("Falha numa tarefa não desfaz o prazo", check tarefas[].criada), the default-responsible side effect (falls to the integration user and may not appear on the lawyer's agenda), how Astrea computes deadlines (skips weekends, its own holiday calendar, forensic recess; considerar_recesso=false disables it; "corridos" does not roll forward), and a caution to confirm the computed date with the user. This is exactly the behavioral context annotations cannot express.

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?

Front-loaded with the core purpose and the prazo-vs-tarefa distinction, then organized in terse per-parameter bullets, so it is easy to scan despite its length. It runs long and a few clauses (e.g. the recesso explanation plus the tribunal-check warning) could be tightened, but essentially every sentence carries decision-relevant information.

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?

With no output schema and 11 parameters, the description compensates fully: it states what is returned (prazo_id, per-task task_id), how to recover from partial task failures, and the key date-computation caveats. An agent has everything needed to call this correctly and interpret the result.

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%, yet the description documents all 11 parameters in prose, including the mutually exclusive due_date vs dias+data_inicial paths, the "uteis"/"corridos" enum semantics, date format AAAA-MM-DD, title length limit, the tag constraint (must allow prazos), and each nested task field including the dias_antes default of falling on the fatal date. It adds materially more than the bare schema types.

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?

States a specific verb and resource ("Cria um PRAZO processual no Astrea") and immediately disambiguates from the adjacent concept: "aparece como prazo na agenda e nos relatórios de prazos, não como tarefa solta". It also names the parent linkage (processo ou caso) and the optional bundled tasks, so the agent can distinguish it from astrea_tarefa_criar and astrea_compromisso_criar without opening schemas.

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?

Explains when this is the right tool (real procedural deadline with agenda/report visibility, optionally with dependent tasks) versus a loose task, and routes follow-up operations to the correct siblings: astrea_prazo_editar, astrea_prazo_cancelar, astrea_prazo_excluir, plus astrea_tarefa_criar for partial failures. It also gives explicit lookup pointers (astrea_processos, astrea_responsaveis, astrea_etiquetas) for resolving referenced ids.

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.