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

Annotations only say it is non-read-only, non-destructive and non-idempotent; the description adds substantial behavioral context: the id is preserved, recreating would generate a new id and detach linked tasks, changing the date does not move linked tasks, and omitting fields leaves them unchanged. These are exactly the side-effect details 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.

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

Front-loaded with the preservation constraint and 'NÃO exclua e recrie' warning before the field bullets, so the critical rule is read first. The per-field bullets are terse and useful; a few items (e.g. sala listed without explanation) add little, but the description is not padded.

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 12-parameter mutation tool with 0% schema coverage and no output schema, this covers the mutation semantics, preserved state, and pointer fields acceptably. The main unresolved item is how bulk mode (hearing_ids/responsible_ids) interacts with the required singular hearing_id, and whether an unsupported bulk call errors.

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 must compensate, and it mostly does: it explains hearing_id's source, start's accepted format and duration-preserving behavior when end is omitted, end's same-day constraint, the modalidade enum, and the identity of title/location/forum/sala/comments/responsible_id. The bulk parameters (hearing_ids, responsible_ids) are only name-dropped without clarifying how they relate to the required hearing_id, leaving one real gap.

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 ('Edita uma AUDIÊNCIA do Astrea no lugar') plus the crucial scope constraint (preserving hearing_id), and explicitly contrasts the tool with delete+recreate. An agent can distinguish it from astrea_audiencia_criar, astrea_audiencia_excluir and the tarefa tools without opening any schema.

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 when-to-use ('redesignar data/hora, mudar modalidade...'), an explicit when-not-to ('NÃO exclua e recrie'), and names the alternatives for adjacent jobs (astrea_tarefa_editar for linked tasks, astrea_responsaveis for ids, astrea_agenda for finding the HEARING id). The partial-update rule ('Informe ao menos um campo; o que você omitir fica como está') removes ambiguity about minimum invocation.

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