consultar_cnpj

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

With no annotations, the description details the return format (JSON) and lists all returned fields. It mentions the external API source (BrasilAPI) and invalid input handling. However, it does not discuss rate limits, error responses, or latency, which would improve transparency.

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 efficient at 4-5 sentences, front-loading purpose and usage. However, the list of return fields is a dense run-on sentence that could be structured better with bullet points or shorter sentences.

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 no output schema, the description thoroughly explains the return values, input handling, and behavioral constraints. It covers all necessary aspects for a single-parameter tool, leaving no major gaps.

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%, baseline 3. The description adds value by clarifying accepted formats (with/without mask, 14 digits) and provides validation guidance beyond the schema, such as rejecting invalid formats without calling the tool.

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 the tool consults Brazilian company data by CNPJ via BrasilAPI and lists the specific fields returned. It distinguishes from sibling tools like consultar_cep or consultar_banco by specifying it's for CNPJ only.

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 explicitly says when to use: when user asks for info about a company identified by CNPJ. It also states what NOT to use (CPF, foreign companies, format validation) and instructs to reject invalid format without calling the tool.

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