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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description still adds real context beyond them: no side effects on tomadores, and that partner CPFs are returned masked — a data-handling detail an agent should know before surfacing results.

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?

One sentence for content and one for routing, with zero filler. The field list is front-loaded before the disambiguation clause, which is the right order.

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, listing the returned fields is exactly the right compensation, and the sibling pointer closes the main ambiguity. Minor gaps remain: nothing about behavior on an unknown/invalid CNPJ (error vs empty result) or whether the lookup is cached/live.

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?

Single parameter with 100% schema coverage, and the schema already says punctuation is optional. The description adds nothing about the cnpj argument, so the baseline 3 applies — the schema does all the work here.

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+resource (fetch registry data for a CNPJ from Receita Federal) and enumerates the returned fields (razão social, situação, CNAEs, endereço, Simples/MEI, sócios). The explicit "Não cria tomador" separates it from the sibling criar_tomador.

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?

Explicitly excludes a plausible misreading ("Não cria tomador") and routes to criar_tomador for the issuing flow, which is strong guidance. However it does not distinguish this from the sibling validar_cnpj, leaving the agent to infer which lookup to use when it only needs validation.

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