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

Annotations already cover readOnly, idempotent, non-destructive and openWorld, so the description correctly spends its space elsewhere: the cost ('Consome 1 requisição'), plan availability ('Todos os planos') and the server-side rejection of generic queries. These are real behavioral facts an agent cannot see in the annotations or schema; only result-set size/pagination behavior is left unstated.

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?

Four short sentences with no filler: purpose first, then valid input shapes, then the rejection rule, then cost and plan. Every sentence carries a decision-relevant fact and nothing is repeated from the schema.

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 six-parameter, zero-required tool with no output schema, the description covers all the combination rules, the credit cost and plan gating, and names the returned fields. It stops short of describing result volume or paging limits, which is the main remaining unknown for an address-scoped person lookup.

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 the schema does not: cep works standalone, logradouro must be paired with cidade and estado, and numero/bairro act as narrowing filters rather than requirements. That 'restrict the result' framing is distinct from the schema's bare 'Opcional' labels, so it earns above baseline.

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 names a specific verb and resource ('Encontra as pessoas') and pins the lookup key to a CEP or a full address, plus the returned fields (nome e CPF). This makes it self-evidently distinct from name-based siblings such as buscar_pessoa_por_nome or ficha_cpf, since the input axis (address) is stated up front.

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 explicit valid input combinations ('Informe cep, ou logradouro com cidade e estado') and an explicit negative rule ('Buscas genéricas (só a cidade ou só o estado) são recusadas'), which is exactly the when-not guidance an agent needs. The gap is that it never points to an alternative tool for the name-only or broad-city case, leaving the routing decision to inference.

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