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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely useful behavior beyond that: it does not consume the daily free quota, it omits contact data, and `incompleto` flags a partial source response. The partial-failure semantic is the kind of detail annotations cannot express.

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?

Three short sentences, front-loaded with the core action and result semantics; each sentence adds a distinct fact (ranking, quota exemption/hidden contacts, `incompleto` meaning). No 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?

With no output schema, the description carries the return burden and does reasonably well, disclosing result count, ordering criterion, contact omission and the `incompleto` sentinel. It could say slightly more about what each suggestion contains (e.g., name vs CNPJ fields), but nothing critical for 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?

Schema description coverage is 100%, so the sole `q` parameter (3-120 chars, name/CNPJ/phone/e-mail) is already fully documented. The description echoes the same accepted inputs without adding syntax, normalization or prioritization rules, so baseline 3 is appropriate.

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 ('Suggests up to 8 Brazilian companies') plus the accepted key types (CNPJ, name, partner, phone, e-mail), so an agent knows this is a fuzzy autocomplete-style lookup rather than a full record fetch. It contrasts implicitly with consulta_cadastro/consulta_cnpj by capping results at 8 and noting it hides contacts, but never names a sibling outright.

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?

Usage is only implied: signaling that it is free of the daily limit and returns a short ranked shortlist hints at exploratory/pre-lookup use, but the description never says when to choose it over search_companies, consulta_cnpj or consulta_cadastro. No explicit when-not conditions are given.

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