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

Annotations declare readOnlyHint=true, destructiveHint=false and idempotentHint=true, but the description centers on mutating flows — editing drafts, discarding with a reason, approving with confirmationToken, and undoing within 24 hours. This directly contradicts the declared safety profile. The later note "Mensagem encaminhada não se recolhe" and the return fields (ACEITO_PELO_PROVEDOR, aceitoEm, enviado) describe a send/approval operation, not a read.

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?

Only the first clause is front-loaded and on-topic; the rest is a dense semicolon-chained run of workflow rules spanning several actions, some of which the tool does not expose. Rules for approval, undo windows, injection signals and e-mail uncertainty are packed together without structure, making it hard to extract what applies to this invocation.

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?

An output schema exists, so return fields need not be spelled out, yet the description spends sentences on return values while leaving triagemId and chaveIdempotente undefined. Given 15 parameters and a multi-step approval workflow, the coverage is broad but muddled by describing mutations the schema and annotations do not support.

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% across 15 parameters, so the description must carry the load, and it does for most of them: estado, clienteId, processoId, canal, pagina (starts at 1), limite (up to 20), avisoId, versaoEsperada, motivo, confirmacaoToken, confirmarRiscoDuplicidade (chave do pedido de risco) and texto all get at least contextual meaning. triagemId and chaveIdempotente remain unexplained.

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?

The opening clause is specific: "listar consulta mensagens com filtros por estado, clienteId, processoId e canal" gives verb, resource and filters. But the description then drifts into "editar salva rascunho", "descartar exige motivo" and "aprovar exige canal EMAIL ou META", actions the schema's acao const ("listar") does not expose, so the actual scope of the tool becomes ambiguous. No sibling tool is named for contrast.

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?

Provides substantial conditional guidance: use avisoId and versaoEsperada from the list, parta do texto exato da prévia and never from the masked version, descartar requires motivo, an uncertain e-mail must be re-approved after 10 minutes or discarded (editar refused), and after 23 hours only the same message with confirmarRiscoDuplicidade. It also routes the agent elsewhere when an injection signal is detected ("faça pelo app"). Lacking only explicit competition guidance against siblings.

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