Skip to main content
Glama

Dados Abertos Senado BR MCP

by io.github.SidneyBissoli

Votações em comissão

senado_votacao_comissao
Read-onlyIdempotent

Lista votações em comissões. O parâmetro por (padrão comissao) define o eixo da consulta: por: comissao → exige siglaComissao; lista as votações daquela comissão. por: senador → exige codigoSenador; lista os votos do senador em comissões (filtro opcional comissao). por: materia → exige sigla, numero e ano (ex.: PL 2630/2020); lista as votações da proposição em comissões (filtro opcional comissao). Em todos os casos aceita período opcional dataInicio/dataFim (YYYYMMDD, filtrado pela data da reunião) e retorna { por, ...contexto, count, votacoes }, cada votação com codigo, data, comissao, reuniao, materia, descricao, totais computados dos votos (totalSim/totalNao/totalAbstencao) e votos (senador, partido, voto). Sem paginação. Períodos amplos podem estourar o tempo-limite da consulta (erro de timeout): prefira janelas de até 3 meses e divida períodos maiores em chamadas sucessivas. Obtenha siglas via senado_listar_comissoes, codigoSenador via senado_listar_senadores; para votações no plenário use senado_votos_materia. Atenção: o codigo de cada votação de comissão pertence a um espaço de numeração próprio e NÃO é válido em senado_obter_votacao (que é exclusivo de plenário) — podem coincidir numericamente, mas apontam para votações diferentes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
anoNoAno da proposição (obrigatório quando por=materia)
porNoEixo da consulta: comissao, senador ou materiacomissao
siglaNoSigla do tipo da proposição (obrigatório quando por=materia; ex: PL, PEC)
numeroNoNúmero da proposição (obrigatório quando por=materia)
dataFimNoData fim (YYYYMMDD)
comissaoNoSigla da comissão para filtrar (por=senador ou por=materia)
dataInicioNoData início (YYYYMMDD)
codigoSenadorNoCódigo do senador (obrigatório quando por=senador)
siglaComissaoNoSigla da comissão (obrigatório quando por=comissao; ex: CCJ, CAE)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A5/5.0
Behavior5/5

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

Annotations already mark this as read-only/idempotent, and the description adds important behavioral context: no pagination, timeout risk on broad periods, recommended 3-month windows, and that returned committee vote codes belong to a separate numbering space. It also describes the response envelope and computed vote totals.

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 paragraph is dense but every sentence carries needed information for a 9-parameter, three-mode tool. The main action and the primary mode are front-loaded, and caveats like timeout and invalid code namespace are placed at the end without bloating the core instructions.

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?

Given the high parameter count, three mutually exclusive modes, and output schema, the description covers required parameters, response structure, filtering, identifiers, and failure/limitation behavior. Nothing essential for correct invocation 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?

Although schema coverage is 100%, the description adds significant conditional logic: which parameters are required for each `por` value, the optional `comissao` filter for two modes, the default `por` value, date format, and a concrete example (PL 2630/2020). This goes well beyond the schema's per-field descriptions.

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 exactly what the tool lists (committee votes), then the `por` parameter disambiguates three concrete query axes. It also distinguishes itself from plenary-vote tools by warning that committee vote codes are not valid in `senado_obter_votacao`.

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?

The description gives explicit mode-dependent rules, names the related tools for getting required identifiers (`senado_listar_comissoes`, `senado_listar_senadores`), and directs plenary vote queries to `senado_votos_materia`. It even states when not to use the code with `senado_obter_votacao`.

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

All Dados Abertos Senado BR MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation2/5

Several tools perform overlapping functions (e.g., senado_buscar_materias vs senado_search_processos, senado_contratos vs senado_contratacoes_lista, and three e-cidadania consultation tools). Although descriptions are detailed, an agent can easily select the wrong one without deep inspection.

Naming Consistency3/5

All tools share the 'senado_' prefix, but the pattern is inconsistent: some use Portuguese verbs (buscar, listar, obter), others English 'search', and some are bare nouns (senado_ceaps, senado_mesa, senado_vetos). This mixed convention reduces predictability.

Tool Count2/5

67 tools is far above the 25 threshold, indicating an overgrown surface. While each tool may serve a niche endpoint, the sheer number makes it difficult for an agent to choose efficiently, and many tools could be consolidated.

Completeness4/5

The toolset covers nearly every aspect of Senate open data (legislative, senatorial, committee, administrative, financial, e-cidadania) with list/detail/searches. Minor gaps exist, such as no direct consolidated contract search, but most workflows can be achieved.

Resources