Consulta sanções de uma pessoa ou empresa por CPF/CNPJ no Portal da Transparência (consolida CEIS — inidôneas/suspensas, CNEP — empresas punidas, e CEPIM — entidades impedidas). Retorna tem_sancao + lista com tipo, órgão, fundamentação e datas. Due diligence / compliance.
| Name | Required | Description | Default |
|---|---|---|---|
| cpf_cnpj | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by specifying the return structure (tem_sancao + list with tipo, órgão, fundamentação, datas) and the consolidated sources (CEIS, CNEP, CEPIM). No contradictions with annotations.
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 concise, using two sentences to convey purpose, data sources, and return information. Every sentence adds value with no redundancy.
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 one required parameter and no output schema, the description adequately explains the return structure and data sources. However, it lacks details on error handling, pagination, or format constraints for the parameter, leaving minor 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 description coverage is 0%. The description does not add any meaning beyond the schema, such as expected format for CPF/CNPJ (e.g., 11 or 14 digits) or validation rules. This is a gap for correct parameter usage.
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 it queries sanctions for a person/company by CPF/CNPJ from the Transparency Portal, consolidating multiple sanction lists. It specifies the return fields and context (due diligence/compliance), distinguishing it from sibling tools that handle other queries like CNPJ consultation or CPF validation.
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 usage for due diligence/compliance but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria for when not to use it. No explicit guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
There is substantial overlap among the process-discovery tools: cnpj_processos, cpf_processos, djen_processos_por_parte, processos_buscar_por_nome, processos_buscar_por_documento, and legal_dossie all lead to finding the same kind of case by party/document, differing mainly by backend and sync/async details. The verbose descriptions mitigate the confusion, but an agent still has to reason through several competing entry points with unclear boundaries.
The set uses domain prefixes and snake_case, but mixes English and Portuguese action verbs (djen_search_comunicacoes vs. djen_processos_por_parte; processos_get_resultado vs. processos_buscar_por_nome) and includes bare-noun names like cnpj_processos, legal_dossie, and transparencia_pep. Platform/utility tools (connect, marketplace, show_version) use a different English naming style, so no single pattern is followed.
30 exposed tools exceeds the scale's heavy threshold and the count is inflated by platform/admin/marketplace meta-tools as well as multiple near-redundant discovery backends. A more scoped legal server could merge the process-finding variants and keep the utility/marketplace features separate.
The server covers a lot of ground—company/CPF data, DJEN and portal discovery, jurisprudence full text, monitoring, transparency, PEP, and sanctions—but there is no native current-case-status/movimentaçoes tool, and the descriptions repeatedly tell agents to enrich with datajud_* tools that are not exposed directly in this list. That is a significant workflow gap for a tool advertised as an alternative to Jusbrasil.