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

With only a thin annotation set (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description carries real behavioral weight: a hard rate limit of 30 AI analyses/day per network, the fact that `ia_filters` consumes the same budget, and the exact failure shape (`limite_diario` with `renova_em`). It also scopes the semantic boundary of the output, which annotations cannot express. Nothing here contradicts readOnlyHint=false — consuming a quota is consistent with a non-read-only tool.

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?

Front-loaded with the core action and mechanism, then limits, then quota mechanics — a sensible ordering with no filler sentences. It is somewhat dense for a three-parameter tool and leans on internal tokens (`ficha.limites`, `limite_diario`, `renova_em`) that inflate the reading cost, keeping it just short of a 5.

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?

There is no output schema, so the description takes on the burden of describing returns and does so: active, opened and closed company counts, how the companies are set up, and a plain reading of the numbers. Combined with the documented fallback response and quota limit, an agent has everything needed to call it and interpret both success and throttled outcomes.

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 `texto`, `uf` and `municipio` are already documented with length limits and examples in the schema itself. The description only restates the high-level idea-to-CNAE-to-place mapping, adding no format or precedence detail (e.g. how `uf`/`municipio` hints interact with a city named in `texto`) beyond the schema. Baseline 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?

The description gives a precise verb-resource pair (evaluates a business idea by counting registered companies) and the mechanism (maps to a CNAE activity code plus a place, then counts active/open/closed companies). It further disambiguates by stating what it does NOT do (no search volume, no demand promise), which separates it from the lookup siblings like consulta_cnpj and search.

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 makes the use context clear (early-stage idea validation against registered-company counts) and points to `ficha.limites` for the interpretation boundary, and it names `ia_filters` as the tool sharing its daily AI-analysis quota. What's missing is an explicit 'use X instead when you need Y' routing rule against the many sibling lookups.

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