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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the burden is lower. The description adds the 50-per-page result cap, which is genuinely useful behavioral context, but says nothing about ordering, empty-result behavior, or lookup failures.

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?

A single short sentence with the resource stated first and no filler or preamble. The trailing "up to 50 per page" is slightly redundant with the schema's page description, which keeps it from being maximally tight.

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 simple two-parameter lookup whose safety traits the annotations already declare, the description is arguably sufficient to call the tool. However, with no output schema, it never indicates the shape or fields of a returned company record, leaving the agent to guess at the response.

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% and both parameters (cep, page) are fully documented inline, including the 8-digit format and 0-based paging, so the baseline is 3. The description's "up to 50 per page" only restates the schema's page semantics rather than adding new meaning.

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 companies registered at a CEP" names a concrete resource and the exact filter (postal code), so an agent knows it returns companies tied to a CEP rather than a single company or an address. It does not distinguish itself from area-style siblings such as raio, vizinhanca, or unidades, which likely overlap in purpose, so it stops short of 5.

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 description gives no when-to-use guidance and never names an alternative, even though the sibling list contains several overlapping lookup tools (consulta_cnpj, raio, vizinhanca, unidades). The only implicit usage signal is the pagination cap, which is about mechanics, not tool selection.

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