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

Annotations only say this is a non-read-only, non-destructive, non-idempotent open-world write. The description adds the critical dry-run semantics, the subscriber notification side effect, retroactive creation for already-closed occurrences, and the one-incident-per-occurrence ceiling — real behavioral context the agent cannot get from the annotations.

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 publishing action and the dry-run/production distinction are front-loaded, then constraints follow. Every sentence carries information: draft fields, gating flag, retroactive case, eligibility, and cardinality — no filler.

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?

With no output schema, the description usefully enumerates what the dry-run returns (título, serviço, início, severidade, status, mensagem) and covers the irreversible publish path, eligibility, and cardinality limit. An agent has what it needs to call this correctly on the first try.

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 coverage is already 83%, so the baseline is 3. The description earns above baseline by explaining the collective role of titulo/mensagem/severidade/status as overrides to the draft, and by restating the confirmar dry-run switch in operational terms rather than just a field description.

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: turns an occurrence (ocorrência) into a PUBLIC incident on the status page, and notes that subscribers are notified. This distinguishes it cleanly from siblings like ver_ocorrencia and listar_ocorrencias, which read occurrences rather than publish them.

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: without `confirmar` it only returns a draft and publishes nothing; with confirmar:true it publishes. It also states exclusions ('só vale pra monitor que aparece na status page'; 'uma ocorrência gera no máximo um incidente'). It does not name a sibling alternative, but the when/when-not guidance is strong and actionable.

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