lookup_cnpj

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

No annotations are provided, so the description carries the full burden. It discloses the data source and what information is returned, which is helpful. However, it does not address behavior such as error handling for invalid CNPJs, network dependency on BrasilAPI, rate limiting, or what happens for inactive/suspended registrations. Decent context but several behavioral aspects remain undisclosed.

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 tightly structured: a one-line purpose statement followed by a compact enumeration of returned fields and the data source. Every sentence earns its place with no redundancy or fluff. Front-loaded with the primary action and resource.

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?

The output schema exists, so return value details are covered elsewhere. With just one parameter at 100% schema coverage, the description is largely complete for what an agent needs: the source, the fields, and the purpose. The only minor gap is behavioral aspects like error handling, but for a single-param public API lookup the description is quite sufficient.

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% and there is only 1 parameter. The schema already documents that cnpj is 14 digits with or without punctuation, and the description complements this by explaining that the tool retrieves Federal Revenue registration data. The description adds the source context and output richness that informs how the single parameter is interpreted. With a single well-documented param, the baseline is inherently high.

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 uses a specific verb ('Look up') with a clear resource ('registration data of a Brazilian company by its CNPJ'). It explicitly enumerates the returned fields (legal name, trade name, status, CNAE, address, partners, share capital), which clearly distinguishes it from siblings like lookup_cep, lookup_ddd, and lookup_cep which target different Brazilian identifiers.

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 identifies the source (Brazilian Federal Revenue via BrasilAPI) and the output shape, which gives useful context. However, it does not explicitly state when to use this vs alternatives, nor any exclusions or prerequisites (e.g., no mention of rate limits, or scenarios where the tool is inappropriate). Usage context is implied rather than explicitly guided.

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