preparar_resposta

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

With no annotations, the description carries the full burden and does well: it enumerates the returned payload (openings, verbs, punctuation, sizes over the last 5 messages; active/cold state; open client points; whether the operator already replied manually) and warns that `responder` reviews and refuses output that exceeds the instructions. It never says whether the call itself is side-effect free or whether it marks the chat as in-preparation, which is the main remaining gap.

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 the imperative call timing, and every clause adds information (return contents, conversation state, numeric instructions, downstream rejection). The middle clause is a dense parenthetical list that is slightly heavy but still 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?

For a one-parameter tool with no output schema and no annotations, the description covers what matters: when to call, roughly what comes back, and how the result feeds `responder`. It leaves the exact shape of `instrucoes` and any state side effects unstated, but nothing critical to correct invocation is missing.

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 description never mentions the single `grupo` parameter. However, schema coverage is 100% and the schema itself documents it as 'slug, nome exato ou jid do chat', so the baseline of 3 applies — the schema does the work and the description adds nothing beyond it.

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 ('prepare reply') plus concrete scope: it returns the account's last-5-message style stats, the conversation state, and numeric `instrucoes` for variation. An agent can immediately distinguish it from `responder`, which is described as the reviewing/sending counterpart.

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 ordering rule: 'Chame ANTES de redigir qualquer mensagem pra um chat' — call before drafting any message. It also names the downstream sibling `responder` and its rejection behavior, so the workflow relationship is clear. It does not state any when-not-to-use case (e.g. group chats vs. DMs, or chats already handled).

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