Skip to main content
Glama

Fichário — CNPJ Brasil

sancoes_pep

Sanções e PEP de uma empresa pelo CNPJ: CEIS, CNEP, CEPIM, acordos de leniência (CGU/Portal da Transparência), dívida ativa da União (PGFN) e sócios que constam como Pessoa Exposta Politicamente (cruzamento por nome + 6 dígitos centrais do CPF; sem expor CPF). Não é análise de crédito.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cnpj": "<cnpj>"
    },
    "name": "sancoes_pep"
  }
}

Input Schema

NameRequiredDescriptionDefault
cnpjYesCNPJ com ou sem pontuação

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden, and it does disclose meaningful behavior: the PEP cross-match is done by name plus the 6 central CPF digits and the CPF itself is never exposed, which is important privacy context an agent could not infer. It says nothing about response shape (per-database flags vs. aggregated verdict), whether an empty result means 'clean', or latency/rate characteristics for what is clearly a multi-source aggregation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence front-loads the resource and then lists sources in a logical order, closed by a short scoping disclaimer. The enumerated acronyms are long but each one earns its place by telling the agent exactly which registries are covered; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description must cover both safety profile and result interpretation, and it only partially does. It is complete on the 'what data sources' axis and on the privacy behavior of the PEP match, but silent on what the returned payload looks like, which matters for a multi-registry aggregation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single required 'cnpj' parameter already documented as accepting punctuated or unpunctuated input. The description only reinforces that lookup is by CNPJ and adds no syntax, validation, or error-handling detail beyond the schema. Baseline 3 applies when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource (sanctions and PEP status of a company, keyed by CNPJ) and enumerates the specific datasets queried: CEIS, CNEP, CEPIM, CGU/Portal da Transparência leniency agreements, PGFN federal active debt, and PEP-matched partners. This is far beyond a restatement of the name. What keeps it from a 5 is that it never explicitly differentiates itself from plausible siblings such as compliance_e_licencas or publicacoes_judiciais, only from the generic notion of credit analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the CNPJ-keyed framing and the closing exclusion 'Não é análise de crédito', which is a genuine when-not signal. However, no sibling alternative is named for the credit-scoring or licensing use cases an agent might confuse this with, and there is no stated precondition beyond needing a CNPJ.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources