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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial context beyond them: data vintage is 2022, census measures describe the sector rather than an individual or the whole postal code, income is not current purchasing power, and company counts are not foot traffic. These are real interpretive constraints an agent would otherwise get wrong. It stops short of saying what the payload looks like or how large it can be.

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?

Purpose is front-loaded in the first sentence, followed by sourcing and then caveats in a compact sequence. The caveat list is dense but each clause warns about a distinct misinterpretation; minor cost is that the trailing caveats read as a run-on list.

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 one-parameter read tool with no output schema, the description does indicate the return content (addresses plus latitude/longitude) and flags the main semantic traps in the data. It lacks any statement about result volume or fields per address, which is the only meaningful 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 description coverage is 100% and the single 'cep' parameter is already documented as '8 digits, with or without the hyphen'. The description adds no format, normalization, or error-handling detail for that parameter, so the schema carries the full burden and the baseline of 3 applies.

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 concrete resource and output: 'The addresses of a CEP (Brazilian postal code), with latitude and longitude', and discloses the underlying data sources (CNEFE, company records, census sectors). It is clear what the tool returns, but it never differentiates itself from close siblings such as consulta_cep, consulta_endereco, or buscar.

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 sentence 'Use the prepared result instead of importing and joining those datasets' gives one usage rule, but it is guidance about reimplementation, not about when to pick this tool over the many sibling address/CEP tools. There are no exclusions or alternative-routing hints.

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