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

Annotations only declare the write/non-idempotent/open-world profile; the description adds the genuinely non-obvious behaviors: dry-run by default returning a draft, notification of page subscribers, retroactive publication of already-closed occurrences, and a cap of one incident per occurrence. It is consistent with destructiveHint=false since later edits/closures are routed to another tool.

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 core action and the publish gate, then prerequisites and the sibling handoff. Every sentence carries information, though the enumeration of draft fields plus the retroactive and one-incident rules make it denser than ideal.

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?

Covers trigger conditions, dry-run vs. real write, side effects on subscribers, edge cases (closed occurrence, non-status-page monitor, duplicate incident), and post-publication routing. With no output schema, the description also describes what the non-publishing call returns, closing the remaining gap.

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 100%, so the baseline is 3, but the description goes further by explaining the draft's contents (título, serviço, início, severidade, status, mensagem) that confirmar returns when false, and by framing titulo/mensagem/severidade/status as overrides to the draft. That workflow-level meaning is not derivable from the schema alone.

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 ('Transforma uma ocorrência em incidente PÚBLICO na status page') and immediately flags the subscriber-notification side effect. It also names the sibling that takes over afterwards (atualizar_incidente), so an agent can distinguish it from related 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?

Explicit about the confirmar gate (draft vs. real publication), the precondition that the monitor must appear on the status page, the retroactive/resolved case for closed occurrences, the one-incident-per-occurrence limit, and the handoff to atualizar_incidente for later updates. Nothing about when to use it is left to inference.

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