compras_fornecedor_cnpj_receita

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

The annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, lowering the burden on the description. The description still adds valuable behavioral detail: 24h caching, provider selection (BrasilAPI/MinhaReceita), and graceful error behavior returning encontrado=false with a diagnostic in _erro instead of throwing exceptions.

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 well-structured with a concise summary up front, a field list, a bolded usage section, and a final behavior/error note. Every sentence serves a clear purpose: identity, return contents, when to use, alternatives, and runtime behavior. It is informative without being bloated.

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?

Given the single parameter, rich annotations, and existing output schema, the description covers all essential context: data source, exact returned information, relationship to sibling tools, non-coverage of sanctions, cache duration, and error semantics. An agent has everything it needs to decide when to call this tool and how to interpret failures.

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%: the single cnpj parameter is already fully documented with length, formatting, and provider configuration via env variable. The description adds no additional parameter-level meaning beyond what the schema provides, so the baseline 3 is appropriate.

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 this is a public CNPJ data lookup from Receita Federal and enumerates the exact returned fields (razão social, CNAEs, QSA, capital social, etc.). It explicitly positions itself as a complement to compras_perfil_fornecedor_completo and distinguishes itself from sanction tools, so an agent can select it correctly among many sibling tools.

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?

There is a dedicated 'Quando usar' section explaining it complements compras_perfil_fornecedor_completo for due diligence. It also explicitly states what this tool does NOT do — it does not check sanctions — and directs the agent to the CEIS/CNEP/CEPIM/CEAF sanction tools instead.

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