Explicar um erro

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description only needs to add behavior beyond that. It does: it discloses the no-match fallback ('Retorna vazio com sugestões se nada bater'), which is the failure mode an agent most needs to know about. It stays silent on result size or ranking when multiple errors partially match.

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 purpose, then coverage, then examples, then the fallback note — a sensible order where every block earns its place. The parenthetical list of example codes is slightly sprawling but functions as matchable evidence rather than filler.

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?

There is no output schema, so the description carries the return contract, and it does: meaning, cause, recommended action, and the related path phase, plus what happens on no match. For a one-parameter lookup tool this leaves no operational 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 adds meaning beyond it: the single `query` accepts either a numeric code or a screen-text fragment, demonstrated with one example of each. That is exactly the ambiguity an agent would otherwise stumble on.

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 ('Traduz um erro da Meta/WhatsApp') plus the exact output shape (significado, causa, o que fazer, fase do caminho). That distinguishes it from diagnostic siblings like wa_diagnose and reference siblings like wa_glossary without opening their schemas.

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?

The two worked examples ('Deu 131037 no envio' -> query="131037") make the trigger condition concrete, and the coverage note (27 errors, both real-world and documented) tells the agent where the tool's knowledge stops. It never explicitly contrasts with wa_diagnose or wa_check_waba, so the agent must infer the boundary.

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