Astrea (Aurum)

astrea_tarefa_criar

Cria uma TAREFA vinculada a um processo no Astrea.

case_id: id do processo (ver astrea_processos).
description: o que fazer.
due_date: opcional, prazo em ISO (ex.: 2026-07-10).
responsible_id: opcional, id do membro do escritório responsável (ver astrea_responsaveis). Se omitir, fica no usuário da integração e pode NÃO aparecer na agenda do advogado, que filtra pelo próprio responsável. Para a tarefa aparecer na agenda de alguém, passe o id dessa pessoa.
repeat: opcional, cria uma SÉRIE recorrente numa só chamada (semanal/mensal/etc.). Exige due_date (vira a 1ª ocorrência). Cada ocorrência é uma tarefa independente (edite/exclua individualmente com astrea_tarefa_editar/_excluir).
kanban_id / column_id: opcionais, colocam a tarefa num quadro kanban (ids em astrea_kanbans). Só column_id = o quadro dessa coluna; só kanban_id = a 1ª coluna (backlog) do quadro. O Astrea só aceita no kanban tarefa COM prazo, então exige due_date. Para mudar a coluna depois use astrea_tarefa_mover.
prazo_id: opcional, vincula a tarefa a um PRAZO processual já existente (id de astrea_prazo_criar ou de um DEADLINE em astrea_agenda); ela aparece dentro do prazo no Astrea. Para criar o prazo e as tarefas juntos use astrea_prazo_criar.
audiencia_id: opcional, vincula a tarefa a uma AUDIÊNCIA já existente (id de astrea_audiencia_criar ou de um HEARING em astrea_agenda). Não combine com prazo_id. Devolve task_id (o id da tarefa criada; na série, um por ocorrência) — guarde para editar/excluir depois.

Bulk support: accepts case_ids, responsible_ids, kanban_ids, column_ids, prazo_ids, audiencia_ids for batched execution.

Input Schema

Name	Required	Description	Default
`repeat`	No
`case_id`	Yes
`case_ids`	No
`due_date`	No
`prazo_id`	No
`column_id`	No
`kanban_id`	No
`prazo_ids`	No
`column_ids`	No
`kanban_ids`	No
`description`	Yes
`audiencia_id`	No
`audiencia_ids`	No
`responsible_id`	No
`responsible_ids`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026
- addedInput schema / properties / audiencia_id
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / audiencia_ids
```
Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
```

Changed2 schema fields changedOct 23, 2026

addedInput schema / properties / prazo_id
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / prazo_ids

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed4 schema fields changedOct 22, 2026

addedInput schema / properties / column_id
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / column_ids

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / kanban_id
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / kanban_ids

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed1 schema field changedJun 30, 2026

addedInput schema / properties / repeat

Added value: +{
+  "properties": {
+    "count": {
+      "type": "number"
+    },
+    "frequency": {
+      "enum": [
+        "daily",
+        "weekly",
+        "monthly",
+        "yearly"
+      ],
+      "type": "string"
+    },
+    "interval": {
+      "default": 1,
+      "type": "number"
+    },
+    "until": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "frequency"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedJun 30, 2026
- addedInput schema / properties / responsible_id
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / responsible_ids
```
Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
```
AddedJun 30, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Although the annotations already establish that this is a non-read-only, non-idempotent mutation without destructive behavior, the description adds substantial operational context. It explains the agenda visibility consequence of omitting responsible_id, the kanban requirement for due_date, the fact that recurrence creates independent tasks, the incompatibility of prazo_id and audiencia_id, and the returned task_id.

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 description is long but appropriately structured as front-loaded bullets for a 15-parameter tool. Most sentences add operational value, though some repetition around kanban and recurrence could be tightened.

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 the absence of an output schema, the description still explains that the tool returns task_id and how it behaves for recurring series. It also covers bulk arrays, parameter interactions, and the main behavioral caveats needed to invoke the tool correctly.

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 carries the burden of explaining parameters, and it does so well for the top-level fields and their interactions. It adds important meaning beyond the schema, especially for responsible_id, repeat, kanban_id/column_id, prazo_id, and audiencia_id, though it does not fully explain the nested repeat fields count, until, and interval.

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 resource: it creates a TASK linked to a process in Astrea. It also distinguishes itself from related operations by naming astrea_prazo_criar for creating deadlines and tasks together, and by describing how this differs from task editing, deletion, and moving.

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?

The description explicitly covers when to use this tool and when to use alternatives: use astrea_tarefa_mover to change kanban column, use astrea_tarefa_editar/_excluir for individual recurring occurrences, and use astrea_prazo_criar to create a deadline and its tasks together. It also warns that omitting responsible_id can keep the task off the lawyer's agenda.

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

All Astrea (Aurum) 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.

astrea_tarefa_criar

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources