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

Annotations already declare read-only and idempotent, and the description adds substantial behavioral context beyond them: data vintage (CNEFE 2022), geocoding basis (postal codes), response flags (base, truncado, lenta), missing-count semantics ('unknown, not zero'), and billing behavior ('lenta:true or missing counts does not consume the allowance or charge credit/x402'). That billing and data-quality disclosure is exactly the kind of context annotations cannot carry.

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?

The purpose and scope are front-loaded in the first sentence, and the sentences are short with little padding. It loses a point because terse fragments like 'Check base, truncado and lenta' introduce unexplained jargon without saying what those flags mean or where they appear.

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 must convey what comes back, and it does mention counts, recent openings, distance, and the base/truncado/lenta flags plus missing-count semantics. It stops short of explaining what base and truncado actually signify, which leaves an agent guessing about result validity.

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 cep/lat/lon/cnae/raio/desde are already documented, and the baseline of 3 applies. The description adds modest value by reinforcing CNAE as an activity code, radius in meters, and that positions derive from postal codes, but it does not clarify precedence between cep and lat/lon or the 'desde' default relative to the data date beyond what the schema says.

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 opening sentence states a specific verb+resource: companies (active, opened, closed) within a radius in meters, filtered by CNAE, returning recent openings and distance. An agent can tell it is a geographic proximity count/list tool. It does not explicitly name the sibling it supersedes (raio, proximo, empresas), so differentiation is inferred rather than stated.

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?

'Query the neighborhood without downloading and indexing both datasets' implies the use case (avoid ingesting two datasets), and the closing sentence gives a clear when-not ('does not measure foot traffic, demand or exact storefront positions'). However, no sibling alternative is named and no explicit trigger conditions ('use this when you have a CEP and want counts by activity') are given.

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