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

Goes well beyond the annotations: states that removing does not delete the tag itself, that existing tags are preserved, that it runs task-by-task, that large batches may return truncated with a 'pendentes' list, and that one failure does not block others. These are exactly the operational details annotations cannot convey.

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?

Front-loaded with purpose, then bulleted parameter and behavior notes — dense but well organized. Slightly heavy for a two-parameter tool, though every point adds value.

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?

Complete for this complexity: prerequisites (tag restrictions), parameter sourcing, batch/partial-failure behavior, and the return shape (tarefas[].ok, 'pendentes') are all covered despite no output schema.

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?

With 0% schema coverage, the description carries the full load: task_ids are task ids (with pointers to discovery tools) and no case_id is needed; tag_ids are tag ids (see astrea_etiquetas) and the tag must permit TASKS in restrictions. This compensates fully for the empty schema.

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 and resource (apply/remove tags on TASKS), including batch scope, and explicitly names the sibling to use for PROCESSOS (astrea_etiquetar). An agent can distinguish it from astrea_tarefa_etiquetar_aplicar/remover 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 concrete use cases (classificar/priorizar, ex.: marcar URGÊNCIA nas atrasadas) plus an explicit alternative for a different resource type. The action semantics (aplicar adds, remover takes away) are spelled out.

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