Skip to main content
Glama

Auditoria de amostra

auditar_amostra
Read-onlyIdempotent

AUDITE ESTA BASE: sorteia indicadores publicados e devolve o necessário para refazer cada um contra o arquivo ORIGINAL da CVM, não contra nós. Use quando: "os números do Dados B3 batem com a CVM?"; "quero conferir uma amostra do ROE". NÃO use para: a fórmula de um indicador → metodologia; todas as fórmulas → dicionario. Fonte e fórmula: VOCÊ escolhe a semente (não aceite sugestão de ninguém, nem de quem pediu a auditoria); sorteio determinístico e reproduzível. Confira em dfp_cia_aberta_.zip de dados.cvm.gov.br, filtrando CD_CVM e ORDEM_EXERC='ÚLTIMO', atento a ESCALA_MOEDA (MIL = milhares). Retorna: casos {empresa, CD_CVM, exercício, indicador, valor publicado, fórmula, conta CVM que AQUELA empresa usou NAQUELE exercício}, audit_id. Vazio ou erro: n vai de 1 a 25. Publique o DENOMINADOR (7 em 100, não "7 divergências"); não transforme "não consegui conferir" em "passou"; erro achado vai a github.com/Val7h/dados-b3-mcp/issues. Acesso: Gratuita, sem chave: auditoria que exige cadastro não é auditoria.

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": {
      "semente": "<semente>"
    },
    "name": "auditar_amostra"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNoQuantidade de casos sorteados, inteiro de 1 a 25 (padrão 25).
sementeYesInteiro à sua escolha; a mesma semente devolve sempre os mesmos casos.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / n / description
      Added value: +"Quantidade de casos sorteados, inteiro de 1 a 25 (padrão 25)."
    • addedInput schema / properties / semente / description
      Added value: +"Inteiro à sua escolha; a mesma semente devolve sempre os mesmos casos."
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description still adds real context: deterministic reproducible sampling, where and how to check against dfp_cia_aberta_<EXERCICIO>.zip (filtering CD_CVM, ORDEM_EXERC, watching ESCALA_MOEDA), the meaning of the returned `casos`/`audit_id`, empty/error behavior, and an issue URL for reporting. It even states the access model (free, no key) and a warning not to accept a seed suggested by the requester — none of which is in structured fields.

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?

Front-loaded with the core purpose in a bolded line, then cleanly partitioned into use/não use, source, returns, error handling and access — easy to scan despite its length. A few rhetorical clauses ('auditoria que exige cadastro não é auditoria') and the inline GitHub URL could be trimmed without losing operational meaning.

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

Completeness5/5

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

For a 2-parameter read-only tool with no output schema, the description supplies the return shape (`casos` fields, `audit_id`), the external verification procedure, error/empty semantics, and how to report a bad result. Nothing an agent needs in order to call it correctly and interpret its output is missing.

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 description coverage is 100%, so the schema already explains both `n` and `semente`, including the same-seed-same-cases guarantee, making the 3 baseline correct. The description adds a bit of intent — the seed must be chosen by the caller and not taken from anyone else — but otherwise restates the schema's 1-25 range and determinism rather than extending it.

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

Purpose5/5

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

States a specific verb+resource: samples ('sorteia') published indicators and returns everything needed to re-verify each one against the original CVM file. It immediately distinguishes itself from `metodologia` (a single indicator's formula) and `dicionario` (all formulas), so an agent can tell it apart from siblings without opening a schema.

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

Usage Guidelines5/5

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

Explicit 'Use quando' section quotes the actual user phrasings that trigger it ('os números do Dados B3 batem com a CVM?') and an explicit 'NÃO use para' section routes formula questions to `metodologia` and `dicionario`. When-to-use, when-not-to-use and alternatives are all named.

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.