Skip to main content
Glama
radar-cnpj-mcp

radar-cnpj-mcp

by wendersoon

Perfil do município

perfil_municipio
Read-only

Summarize a Brazilian municipality’s economy in one call: active companies, top sectors, company size, MEI share, registration status, and 12-month opening trends versus the prior year.

Instructions

Resume a economia de um município em uma chamada: empresas ativas, principais setores, porte, percentual de MEIs, situação cadastral e aberturas dos últimos 12 meses completos comparadas aos 12 anteriores. Retorna só totais, sem listar empresas.

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": {
      "municipio": "<municipio>"
    },
    "name": "perfil_municipio"
  }
}

Input Schema

NameRequiredDescriptionDefault
ufNoUF do município. Necessária em caso de homônimos.
municipioYesNome do município, sem diferenciar acentos.
principais_setoresNoQuantos setores (CNAE principal) listar.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds meaningful behavior beyond that: it returns aggregates only, never a company list, and it pins the comparison window to the last 12 complete months against the prior 12. It stops short of describing response shape or what happens when the locality is ambiguous.

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 sentences, no filler, with the payload inventory front-loaded and the scope limitation placed last where it reads as a boundary. Every clause carries information an agent needs.

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

Completeness4/5

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

For a 3-parameter, read-only aggregate tool with no output schema, the description covers scope, data domains, and the time comparison. It could still say whether figures are per-municipality absolute counts and how the sector list is ordered, but nothing critical to invoking it correctly 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 uf, municipio, and principais_setores are fully documented in the schema, including the homonym rule and the CNAE sector count bounds. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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?

The description uses a specific verb ("Resume") plus an explicit enumerated content list: active companies, main sectors, size, MEI percentage, registration status, and 12-month opening comparisons. The closing clause "Retorna só totais, sem listar empresas" separates it from listing-oriented siblings such as buscar_empresas. An agent can tell exactly what this tool delivers without opening the schema.

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?

"Em uma chamada" implies this is the overview/efficiency choice, and "sem listar empresas" hints that listing tools exist for detail. However, no sibling is named and no when-not condition or prerequisite (e.g. resolving the município, dealing with homonyms) is stated. Usage is inferable but not instructed.

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