lex-rag

Overview Schema Source Related Servers Discussions Admin

pesquisar_norma

Search Brazilian federal legislation and STF binding precedents via semantic query, returning exact statutory text with URN-LEX and official source URLs.

Instructions

Pesquisa a base jurídica federal por busca semântica + reranking.

Devolve o texto literal de cada dispositivo com URN-LEX e URL da fonte
oficial. Use para perguntas jurídicas sobre a Constituição, leis
complementares, leis ordinárias e decretos federais — e sobre as Súmulas
Vinculantes do STF, que entram no mesmo resultado que a legislação (uma
consulta sobre nepotismo traz o art. 37 da CF e a Súmula Vinculante 13).
As 736 súmulas simples do STF (não vinculantes) também estão no corpus,
com a situação que o próprio STF publica (cancelada, revogada, superada).

Para perguntas de processo legislativo e de rito das Casas, o corpus tem os
regimentos internos (RISF, RICD e Regimento Comum), os Códigos de Ética
parlamentar, a resolução de tramitação de MPs e a da CMO (tipo "regimento"),
além das resoluções do Senado do art. 52 da CF — limites de dívida e de
crédito dos entes, alíquotas de ICMS e ITCMD (tipo "resolucao").

Filtros opcionais: ``tipo_norma`` restringe por espécie ("constituicao",
"lei_complementar", "lei", "codigo", "decreto", "regimento", "resolucao",
"sumula_vinculante", "sumula_stf");
``urn_lex`` restringe a um documento específico (ex.:
'urn:lex:br:federal:lei:2018-08-14;13709' para buscar só na LGPD).

Súmula cancelada ou de publicação suspensa fica fora do resultado enquanto
``somente_vigente`` for verdadeiro, e vem marcada como não vigente quando
ele é desligado.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limite`	No
`urn_lex`	No
`consulta`	Yes
`tipo_norma`	No
`somente_vigente`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Sep 23, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses the search mechanism (semantic + reranking), the output format (literal text with URN-LEX and URL), and the status behavior of summaries (canceled/suspended excluded when somente_vigente is true, marked as non-vigente otherwise). This goes beyond the schema and gives the agent a clear mental model of the tool's behavior.

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?

The description is long (multiple paragraphs) but each paragraph adds essential information: purpose, return format, coverage, filters, and status behavior. It is front-loaded with the core purpose and structured logically. Some redundancy exists (e.g., repeating the list of document types), but overall it is well-organized and information-dense without excessive padding.

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 tool with 5 parameters, an output schema, and no annotations, the description covers the main use cases, document coverage, filter semantics, and edge cases (canceled summaries). It does not explain how limite affects result count or any pagination, but given the output schema exists and the core behavior is well described, the description is largely sufficient for correct invocation.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must explain parameters. It does this well for tipo_norma (enumerating all allowed species), urn_lex (with an example), and somente_vigente (behavioral explanation). limite is not described, but it is a simple integer with a default. The description adds substantial meaning to three of the five parameters, compensating for the schema gap.

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 clearly states the tool searches the federal legal base using semantic search plus reranking, and specifies the returned data (literal text, URN-LEX, URL). It lists the covered document types (Constitution, laws, decrees, binding and non-binding summaries, internal regulations). However, it does not explicitly differentiate from sibling tools like buscar_por_assunto, leaving some ambiguity for an agent choosing between them.

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?

The description provides rich context on what to use the tool for ('Use para perguntas jurídicas sobre...') and even gives example queries (e.g., nepotism bringing both art. 37 and Súmula Vinculante 13). It also explains coverage of legislative process documents. However, it never mentions when NOT to use this tool or points to alternative sibling tools, leaving the agent to infer distinctions.

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

Deploy Server