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

Annotations already declare a non-readOnly, non-destructive, non-idempotent mutation, and the description usefully adds partial-update semantics ('o que você omitir fica como está') and the no-duplication guarantee, which is exactly the context an agent needs before editing in place. It stops short of covering auth/permission requirements or failure behavior on a bad id.

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 purpose and the key 'omit = unchanged' rule are front-loaded, and per-field notes are cleanly bulleted. The bulk behavior is stated twice (once in Portuguese, once as a trailing English 'Bulk support' sentence), which is one redundant line in an otherwise tight definition.

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?

For a mutation tool with no output schema, the description covers the essentials: partial-update semantics, label handling, parameter provenance, and batch rules. It leaves only edge behavior (invalid task_id, permissions, whether case_id must match the task) unaddressed.

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 must carry the load. It documents task_id (with its provenance), case_id, description, due_date with the AAAA-MM-DD format, and responsible_id with a lookup reference — good value. However, the three array parameters (task_ids, case_ids, responsible_ids) are only alluded to in one vague 'bulk support' sentence with no explanation of how they interact with the singular required fields.

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?

States a specific verb+resource ('Edita uma TAREFA existente') and immediately qualifies the mode of mutation ('altera no lugar, sem duplicar'), which separates it from astrea_tarefa_criar. It also names the sibling to use for the one adjacent operation (labels → astrea_tarefa_etiquetar), so an agent can route 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.

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

Gives explicit conditions: supply at least one field to change, omitted fields are preserved, and label changes must go to astrea_tarefa_etiquetar. It also explains the batch constraint (call once per task unless all tasks share a case_id). The closing English 'Bulk support' line slightly muddies that rule rather than clarifying it, keeping this just short of 5.

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