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

Beyond the annotations, the description discloses important behavior: due_date is mandatory and must be precomputed, omitted responsible_id defaults to the integration user and may not appear in the lawyer’s agenda, tags must permit deadlines, and task failure does not roll back the deadline. It also explains the return values and the fact that changing the deadline date later does not recalculate tasks, which is exactly the kind of behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and the key distinction from loose tasks, then moves into parameter semantics and operational caveats. Despite being detailed, every section adds useful information for correctly invoking a multi-parameter mutation tool with nested task creation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters, no schema descriptions, no output schema, and non-idempotent mutation behavior, the description is complete enough to call the tool safely. It covers required inputs, optional inputs, nested task semantics, return values, failure recovery, and later-edit limitations.

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

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 well: it documents case_id, title, due_date, responsible_id, comments, tag_ids, and the nested tarefas structure including due_date versus dias_antes and per-task responsible_id. It also adds format and constraint details not present in the schema, such as AAAA-MM-DD and the 250-character title limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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 procedural deadline (PRAZO) in Astrea, linked to a process/case and optionally to dependent tasks. It explicitly distinguishes the result from a loose task by saying it appears in the agenda and deadline reports, so an agent can identify what this tool creates.

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

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

It gives a concrete usage example, explains that the deadline date must already be calculated, and clarifies the relationship to task creation by stating that failed tasks should be recreated individually with astrea_tarefa_criar plus prazo_id. It does not explicitly compare this tool against every nearby sibling such as astrea_compromisso_criar, but the main usage context is clear.

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