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

Annotations only declare the basic safety profile (not read-only, not destructive, not idempotent, closed-world); the description adds materially more: timestamps are interpreted in the server timezone (UTC), end defaults to start + 30 min, repeat creates independent occurrences editable/deletable individually, and — the key gotcha — omitting responsible_id can leave the compromisso off the lawyer's agenda. It also discloses the return value (appointment_id, one per occurrence).

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 purpose and the sibling warning before the parameter bullets, and given 10 parameters at 0% schema coverage the length is earned. The trailing English 'Bulk support' line is abrupt and stylistically inconsistent with the otherwise Portuguese, per-parameter structure.

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?

There is no output schema, but the description compensates by naming the returned appointment_id and its per-occurrence behavior; defaults, timezone and series semantics are all covered. It stops short of explaining batch/cross-product behavior for case_ids + responsible_ids and says nothing about failure modes (e.g., invalid case_id or responsible_id).

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 mostly delivers, documenting case_id, title, start (with ISO example), end, all_day, location, responsible_id and repeat semantics beyond the bare schema. The gap is the batch variants: 'accepts case_ids, responsible_ids for batched execution' is a single English sentence that never explains how the combination behaves or how returned appointment_ids map back to inputs, and repeat's count/until/interval are undocumented anywhere.

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 ('Cria um COMPROMISSO/evento na agenda, vinculado a um processo no Astrea') and immediately distinguishes it from the closest sibling, astrea_audiencia_criar, with the reason (a compromisso becomes a meeting event and does not appear in hearing filters/reports). An agent can select this without opening either 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 an explicit when-not rule ('Para AUDIÊNCIA use astrea_audiencia_criar') and points to the tools needed to obtain prerequisite IDs (astrea_processos for case_id, astrea_responsaveis for responsible_id). The edit/delete siblings are named for follow-up operations, so the full lifecycle is routable.

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