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

With no annotations provided, the description must disclose behavior, but it only describes the resource. It does not state that this is a read-only lookup, what occurs if the CNPJ is not found, whether multiple records could be returned, or any access constraints. The singular 'Um estabelecimento' implies one record, but this is implicit.

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 a single sentence with no filler. The scoping by CNPJ is front-loaded, and the field enumeration is succinct. Every word contributes to conveying the tool's core subject.

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 and no annotations, the description must explain the operation and expectations. It lists some output fields but does not explicitly say this is a lookup operation, does not cover error behavior, and does not situate the tool relative to its siblings. An agent would remain uncertain about the return envelope and failure modes.

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?

The input schema only defines 'cnpj' as a string with no description. The description adds crucial semantics by specifying the CNPJ must be 14 digits and that it is the selection key for the establishment. This helps the agent construct a valid request, though it does not detail validation rules.

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 identifies the tool as providing an establishment for a given 14-digit CNPJ and lists the included fields (situação, atividade, município IBGE, porte, capital). This distinguishes it from the sibling tools, which handle counting, listing, and data caveats. The lack of an explicit verb like 'retrieve' or 'get' prevents a perfect score.

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?

No guidance is given about when to use this tool versus the siblings. There is no mention of selecting this tool when you have a specific CNPJ and need establishment details, nor any exclusion of alternatives. The agent must infer the usage context from the resource-focused description.

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

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

With no annotations, the description carries the behavioral burden. It discloses a non-obvious transformation ('município já vem convertido para IBGE') and clarifies that the count reflects entries by CNAE principal, which prevents misinterpretation of the result. It does not cover output format or data freshness, but the key behaviors are surfaced.

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 dense sentences with no filler. The main capability and dimensions are front-loaded, and the caveats are placed immediately after, making the description efficient and scannable.

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 9 parameters, no output schema, and no annotations, the description should do more to explain the response shape and when to use this tool. It provides two important caveats but omits result format, pagination/limit behavior, and explicit routing among the sibling tools, leaving the agent with incomplete context.

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 89%, so the schema already documents most parameters. The description adds meaningful parameter-related semantics: it warns that Receita municipality codes differ from IBGE codes and clarifies that the count is based on the principal CNAE, which is not fully captured in the schema.

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 ('Contagem') and resource ('estabelecimentos (ou empresas)') and lists the grouping dimensions: município, UF, CNAE, grupo, porte, situação. It does not explicitly contrast with sibling tools like empresas_listar, but the counting verb clearly differentiates it from listing or single-CNPJ 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?

The description implies use when aggregate counts are needed and specifies the data source (official Receita dump), but it does not explicitly say when to prefer this over empresas_listar, empresas_cnpj, or how to handle caveats via empresas_data_caveats. Usage context is implied rather than stated.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the content (caveats, evidence, build report) but not behavior such as return format, whether the optional id filters results, side effects, or read-only status.

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 a single compact sentence with no filler. It front-loads the main subject ('armadilhas do dump do CNPJ') and adds meaningful detail about evidence and the build report.

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 tool with an undocumented parameter and no output schema, the description is not complete enough. It gives content context but omits how the optional id is usedSuccessful.

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?

The schema has a single optional id parameter with 0% schema description coverage. The description does not mention the parameter at all, leaving the agent to guess what id refers to and how it affects the returned caveats or build report.

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 identifies the tool's content: CNPJ dump pitfalls with evidence and the build report, including month, cut, and unmatched municipalities. This distinguishes it from the sibling listing/counting tools, though it uses a noun phrase rather than an explicit verb like 'returns' or 'shows'.

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 no explicit guidance on when to use this tool versus the siblings (empresas_contagem, empresas_listar, empresas_cnpj). The reader must infer that this tool is for data quality caveats, but no usage context or exclusions are provided.

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

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

Não há annotations, então a descrição carrega o ônus da transparência. Ela revela os campos do retorno, a ordenação por capital social e restrições de dados (razão social apenas para PJ, ausência de contatos/sócios). Faltam detalhes como paginação e formato exato da resposta, mas para um listador a transparência é boa.

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?

Duas frases objetivas, começando pela ação principal e pelo escopo. Não há repetição do schema nem conteúdo supérfluo; cada oração agrega informação sobre o que é listado, a ordenação e as limitações do resultado.

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?

A ferramenta tem 8 parâmetros, nenhum obrigatório, sem output schema e sem annotations, o que aumenta a necessidade de contexto. A descrição cobre bem campos, ordenação e limitações, mas não detalha combinações de filtros, comportamento sem filtros geográficos ou formato da resposta.

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?

Com 88% de cobertura no schema, os parâmetros já estão bem documentados estruturalmente. A descrição acrescenta contexto sobre o recorte e a ordenação, mas não explica a relação entre uf, municipio e municipios nem se algum filtro geográfico é esperado/obrigatório.

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?

A descrição usa verbo específico ('Lista') e recurso claro (estabelecimentos por município/UF), além de informar ordenação e campos retornados. Não nomeia as ferramentas irmãs explicitamente, mas o escopo e o verbo já diferenciam bem de empresas_contagem, empresas_cnpj e empresas_data_caveats.

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?

Há contexto implícito de uso: a ferramenta serve para listar estabelecimentos filtrados por município ou UF, e a descrição informa limitações relevantes (sem e-mail, telefone ou sócios). Porém, não há orientação explícita sobre quando preferir as alternativas nem sobre exclusões ou pré-requisitos.

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