Skip to main content
Glama
Juris Licita MCP
by bitbusca

Empresas por filtro (base CNPJ)

buscar_empresas
Read-onlyIdempotent

Lists companies from the Brazilian CNPJ database by state, city, neighborhood, CNAE, size, and opening date, excluding partner details, for legal and procurement research.

Instructions

[Avançado: exige BITBUSCA_API_KEY] Lista empresas da base de CNPJ por UF, município, bairro, CNAE, porte e data de abertura (sem sócios).

Input Schema

NameRequiredDescriptionDefault
ufNoUF (ex.: MS).
cnaeNoCNAE(s), separados por vírgula.
pageNoPágina (começa em 0).
porteNoPorte (ME, EPP, DEMAIS).
bairroNoBairro.
pageSizeNoLinhas por página (padrão 25).
municipioNoMunicípio (nome ou código IBGE).
aberturaDiasNoAbertas nos últimos N dias.
somenteAtivasNoSó situação ATIVA.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=true, so the safety profile is covered. The description adds two pieces of context beyond that: the API-key entitlement gate and the content boundary '(sem sócios)', which tells the agent partner data is not returned. It omits result shape and pagination behavior.

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

Conciseness5/5

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

Two compact clauses: the entitlement warning is bracketed and front-loaded so it is seen before anything else, followed by a single sentence covering verb, data source and filters. No filler and nothing repeated from the schema.

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 nine optional parameters, no required fields, idempotent/read-only annotations and a fully described schema, the definition covers invocation well. The gap is that there is no output schema, yet the description says nothing about the row shape returned or that paging is capped at page 20 with 25 rows by default, so the agent cannot anticipate the result envelope.

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%: all nine parameters, including page, pageSize, somenteAtivas and aberturaDias, are documented in the schema itself. The description only names the filter families and adds no syntax detail (e.g. multiple CNAEs comma-separated, município accepting name or IBGE code), so it sits at the baseline for high-coverage schemas.

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 gives a concrete verb ('Lista') and a concrete resource ('empresas da base de CNPJ'), then enumerates the filter dimensions (UF, município, bairro, CNAE, porte, data de abertura). The parenthetical '(sem sócios)' implicitly separates it from the single-company lookup sibling consultar_cnpj, but it never names that sibling, so differentiation is inferential rather than explicit.

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?

It states a real precondition ('Avançado: exige BITBUSCA_API_KEY'), which tells the agent when the call will fail, and the filter list implies a bulk/segment search use case. However, it never says when to prefer this over consultar_cnpj for a single company or buscar_editais_bitbusca for procurement notices, leaving the routing decision to inference.

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