Brazilian company data by CNPJ from Receita Federal: partners, CNAE, address, debts and sanctions.
Scored across 1 tool
There is only one tool, so there is no possibility of confusion with a sibling tool. Its purpose—fetching public Brazilian company data by CNPJ—is stated unambiguously, including accepted input formats.
The single name consultar_cnpj follows a clear verb_noun pattern in consistent snake_case Portuguese. With only one tool there are no cross-tool naming conflicts to evaluate.
A one-tool surface is thin in the abstract, but the server's scope is a single-purpose CNPJ lookup, so one tool genuinely covers the job. A batch or supplementary variant could add value but is not required.
The lookup returns a very broad field set (registration, CNAE, contacts, partners, debt and sanction lists) covering the entity-detail use case fully for read-only access. Gaps are minor: no batch/CNPJ list input and no search by company name.
Dados públicos de uma empresa brasileira ativa, da Receita Federal: razão social, nome fantasia, abertura, natureza jurídica, porte, Simples, capital social, atividades (CNAE), endereço, telefones, e-mail e sócios, e se consta na dívida ativa da União, no CEIS, no CNEP ou na lista do trabalho escravo; com chave, o valor e a situação da dívida e as sanções. Aceita CNPJ numérico ou alfanumérico, com ou sem pontuação.
| Name | Required | Description | Default |
|---|---|---|---|
| cnpj | Yes | O CNPJ, como 11.222.333/0001-81 ou 11222333000181 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: data provenance (Receita Federal), the full field surface returned, and the accepted input formats including alphanumeric CNPJs. It omits error/not-found behavior and any rate-limit or caching traits.
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?
Two sentences: the first front-loads the source and then enumerates returned fields (valuable since there is no output schema), the second covers input formats. The long field list earns its place because it substitutes for a missing return schema.
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?
With no output schema, the field enumeration makes the description largely self-sufficient, and the input-format sentence closes the main calling ambiguity. What remains uncovered is edge-case behavior — what happens for inactive, invalid, or not-found CNPJs — which matters for a single-param lookup but is secondary.
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 the baseline is 3, but the description genuinely adds meaning the schema lacks — the schema example only shows numeric formats ('11.222.333/0001-81' or '11222333000181'), while the description states that alphanumeric CNPJs are also accepted, with or without punctuation.
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 names a concrete lookup resource (public data of a Brazilian company from Receita Federal) and enumerates exactly what comes back — legal name, CNAE, address, partners, debt/sanction flags. An agent knows precisely what this tool retrieves without opening the schema.
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?
Usage is implied: it is a CNPJ-keyed company lookup, and the phrase 'empresa brasileira ativa' hints at active-company scope. But there is no explicit when-to-use guidance, no statement about behavior for inactive or nonexistent CNPJs, and no alternatives to route to (none exist among siblings).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
consultar_cnpjBrazilian company and person data by CNPJ/CPF: registry, partners, tax status, sanctions, lawsuits.
Empresas, sócios e conexões por CNPJ. Brazilian company data, ownership and corporate networks.
Free lookup of 28.4M active Brazilian companies by CNPJ or name (Receita Federal open data).
Brazilian business data for AI agents. Public company dossiers by CNPJ.
Add one secure layer between your agents and this server.