Skip to main content
Glama

Gover MCP

by io.github.pedro381
OverviewDiscussionsAdmin

Executar relatório homologado do Gover

gover_executar_relatorio
Read-onlyIdempotent

Executa um relatório homologado do Gover e devolve as linhas para montar a resposta ou o relatório ao usuário. Use a chave e os filtros de gover_metadados_relatorio. Datas SEMPRE em yyyy-MM-dd (dd/MM/yyyy é aceito e convertido como data brasileira; a conversão aparece nos avisos). NÃO inclua ClienteId nem UsuarioId: vêm da sessão autenticada e delimitam o que a pessoa pode ver. Filtros omitidos valem "todos". quantidade=0 é sucesso sem registros. Relatórios marcados "sem-permissao" no catálogo executam normalmente (marcação antiga); se o banco negar, a resposta explica e você oferece alternativa. Só os marcados "erro" são recusados antes do banco, salvo tentarMesmoIndisponivel=true a pedido explícito do usuário. Formate pelas colunas devolvidas, cite o relatório e o período, e não arredonde valores monetários originais. Relatórios "-detalhe" contêm dado pessoal: apresente só o necessário. Somente leitura.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chaveYesChave do relatório, ex.: "dados-gerais". Obtenha em gover_listar_relatorios.
filtrosNoFiltros do relatório pelos nomes dos metadados, ex.: {"DataSolicitacao_Inicio":"2026-01-01","DataSolicitacao_Termino":"2026-01-31"}. Sem ClienteId/UsuarioId/Timeout.
timeoutNoSegundos de execução no banco (1 a 600; padrão 120). Suba para 300 em períodos longos de relatórios de detalhe.
tentarMesmoIndisponivelNoSó true quando o usuário pedir explicitamente para tentar um relatório marcado com "erro" (objeto inválido no banco). Não é preciso para "sem-permissao".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tentarMesmoIndisponivel / description
      Previous value: -"Só true quando o usuário pedir explicitamente para tentar um relatório marcado sem-permissao/erro."New value: +"Só true quando o usuário pedir explicitamente para tentar um relatório marcado com \"erro\" (objeto inválido no banco). Não é preciso para \"sem-permissao\"."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already provide readOnly/idempotent hints, but the description adds substantial behavior: date format conversion with warnings, session-bound auth scoping, omitted-filter semantics, 'quantidade=0 is success with no records', 'sem-permissao' reports run normally while 'erro' reports are refused unless explicitly requested, and PII caution for '-detalhe' reports. No contradiction 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.

Conciseness5/5

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

The description is long but dense: every sentence earns its place, with the core purpose and output first, then invocation rules, then edge cases and formatting. There is no filler or repeated schema content.

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?

There is no output schema, but the description compensates by defining return rows/columns, formatting expectations, success-with-zero-records, authentication boundaries, execution failure behavior, and personal-data handling. Nothing an agent needs to call this correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics beyond the schema: dates must be yyyy-MM-dd with automatic Brazilian parsing, ClienteId/UsuarioId are forbidden, omitted filters mean 'all', timeout guidance says to raise to 300 for long/detail reports, and tentarMesmoIndisp... is reserved for explicit user requests. This materially helps an agent fill parameters correctly.

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 opening sentence states a specific verb and resource: 'Executa um relatório homologado do Gover e devolve as linhas...' and explains the output's purpose. This clearly distinguishes it from related catalog/metadata tools such as gover_listar_relatorios and gover_metadados_relatorio.

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

Usage Guidelines4/5

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

The description gives clear usage context: use the key and filters from gover_metadados_relatorio, omit ClienteId/UsuarioId because they come from the session, and treat omitted filters as 'todos'. It also explains when the tentarMesmoIndisp... flag is appropriate; the only gap is that it never explicitly names a when-not-to-use case or a sibling alternative to switch to.

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

All Gover MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources