compras_sancao_cnep

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

The description mentions 'Cache 1h' (1-hour cache), which is useful behavioral info. However, there are no annotations provided, and the description does not detail other behaviors like rate limiting, data freshness guarantees, query result limits, or what happens with empty results. For a tool querying a government punitive registry, this is under-specified.

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 description is brief (5 lines), front-loading the tool name and legal reference. Every sentence provides distinct information: endpoint, law reference, purpose, and caching. However, the newline-separated format is slightly disorganized and could be streamlined.

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?

Despite having no annotations and an output schema, the description is missing key details like what data fields are returned (useful given no output schema visibility), how pagination works (e.g., total results count), or whether the tool supports partial matches on 'nome'. With complexity moderate (3 params) and full schema coverage, a 3 is appropriate—adequate but not thorough.

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 coverage is 100%, so baseline is 3. The description does not add new meaning to the parameters; it only names the tool's purpose. The schema already documents 'cnpj' as CNPJ (14 digits, with/without punctuation), 'nome' as sanctioned name, and 'pagina' as 1-based page. The description adds no nuance (e.g., whether filtering by CNPJ and nome is AND or OR, or if pagination returns all results).

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 clearly states it consults the CNEP (National Registry of Punished Companies) under the Anti-Corruption Law. It identifies the specific resource (punished companies) and the legal framework, distinguishing it from broad search tools. However, it lacks differentiation from other 'sancao' siblings like compras_sancao_ceis, compras_sancao_ceaf, and compras_sancao_cepim, which also deal with sanctions.

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?

No explicit guidance is given on when to use this tool versus alternatives like compras_sancao_ceis (which might cover different sanctions/levels). It mentions 'risk of integrity indicator' but doesn't explain selection criteria. There are no when-to-use, prerequisites, or exclusions provided.

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