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

The description goes well beyond the annotations, which already indicate non-readonly, non-idempotent, and destructive behavior. It explains that sends are external and repeating can duplicate, delete depends on the bot's current permission, 401/403 require reviewing access, 429 requires respecting Retry-After, timeout does not prove absence of effect, and preview never applies the change. It also details the confirmation_id flow. This is exactly the contextual behavioral information that structured annotations cannot convey.

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 description is well-structured with labeled sections (Finalidade, Use quando, Escolha da operação, Parâmetros, Efeitos e falhas) and front-loads the purpose. Every sentence delivers distinct operational, safety, or failure-handling information with no filler or repetition. The length is proportionate to the tool's complexity of 10 operations and nested conditional inputs.

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?

Given the tool's high complexity, an output schema, and rich annotations, the description covers purpose, alternatives, operation selection, parameter provenance, failure handling, rate limits, timeouts, preview behavior, confirmation flow, and destructive effects. Nothing essential to correct invocation appears missing; return-value details are appropriately left to the output schema.

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 100%, so the baseline is 3. The description adds meaningful guidance: messageId, groupJid, and participants must come from authorized queries; list uses period/search/limit-offset; poll_send expects question/options; reply needs the source message; broadcast_send should reuse the preview-reviewed selection; and confirmation_id must accompany confirmation. This aids correct parameter use, but it does not exhaustively describe every nested field (e.g., buttons, recurrencePattern), which is acceptable since the schema handles those.

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 states the tool's purpose explicitly: consult accessible message history and perform immediate sends or deletions to authorized destinations. It enumerates the specific operations (list, get, broadcast_preview, send/reply/admins_send/buttons_send/poll_send, broadcast_send, delete) and differentiates from siblings such as schedules_manage, workflows_design, and integrations_manage. This is a specific verb+resource with clear sibling differentiation.

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?

A dedicated 'Use quando' section says when to use this tool (search/read messages or deliver now) and explicitly routes other scenarios to siblings: future delivery to schedules_manage, multi-step processes to workflows_design, live alerts to integrations_manage. It also provides per-operation selection guidance, so the agent knows exactly when and how to choose the right operation. This is explicit and leaves no ambiguity.

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