estado_triagem

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

With no annotations, the description carries the full behavioral burden, and it does disclose meaningful semantics beyond the return field list: autonomo true means it sends directly while absence means confirmation is required before sending. Read-only nature is implied by "Retorna" but never stated, and nothing is said about authentication or the volume/size of the returned state.

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?

Two sentences, front-loaded with what is returned before the field semantics and the scope exclusion. The slash-delimited field enumeration is dense and slightly run-on, but since there is no output schema it genuinely earns its place.

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?

Because no output schema exists, the description must explain the return value, and it does so at the field-name level with semantics given for the autonomo flag. It leaves the meaning of several returned fields (muted, notes, lastSeen format) and what the response shape looks like largely unexplained for a tool whose entire job is returning a composite state object.

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?

The tool takes zero parameters, so there is nothing for the description to clarify beyond the schema. Baseline 4 applies; the description correctly spends no space on arguments.

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 description opens with a specific verb and resource ("Retorna o estado de triagem inteiro") and enumerates exactly which fields come back (resolved/muted/notes/lastSeen/copilot/alertar/autonomo/etiquetas/agente/executor). It explicitly delimits scope against siblings, stating that client contract data is not here and lives in dashboard and definir_contrato, so an agent can distinguish it from neighbors without opening a 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?

It gives clear purpose context — the AI reads it to learn what has already been handled, which chats are under copilot, which alert, and the send mode per chat — and it names an explicit exclusion plus the alternatives to use instead (dashboard, definir_contrato). It does not, however, say when in a workflow to call it versus siblings like agenda_ver or status_envio.

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