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

With no annotations, the description carries the full burden and delivers unusually valuable context: the $0.10 price, the sanctions sources, source-freshness reporting, an explainable heuristic, and the explicit caveat that results are never valid for automatic AML/credit approval. It omits error behavior on invalid CNPJ and any latency/rate-limit notes, which keeps it from a 5.

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?

A single dense sentence plus disclaimer and price, front-loaded with the tool's identity and payload. Every clause earns its place (sources, heuristic nature, review requirement, cost); only the slight run-on density keeps it off 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?

For a one-parameter lookup with no output schema and no annotations, the description tells the agent what the response conceptually contains and the boundary conditions of its use. It is nearly complete; the only gaps are error/invalid-input behavior and any auth or rate-limit expectations.

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?

There is a single required parameter with 100% schema description coverage, so the schema already documents the CNPJ format (formatted or unformatted, numeric or alphanumeric per IN RFB 2.229/2024). The description adds nothing about the parameter, which is the baseline-3 case when the schema does the work.

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 a KYB lookup that returns structured Brazilian registration data, CGU CEIS/CNEP sanctions, source freshness, and a NON-credit risk heuristic. It is specific about the resource and outputs, but never names which sibling (get_company, get_company_dossier, get_company_score, check_sanctions) it should be preferred over, leaving overlap unresolved.

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?

'Human review required; never automatic AML/credit approval' and 'NON-credit risk heuristic' imply the intended compliance context and a hard usage limit on downstream automation. However, there is no explicit guidance on when to pick this versus get_company_score, check_sanctions, or get_company_dossier, so routing is left to inference.

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