Skip to main content
Glama

Biblioteca fiscal de Cumplida · edición abierta (gratuita)

Buscar precedentes

buscar_jurisprudencia
Read-onlyIdempotent

Busca precedentes mexicanos (SCJN, Plenos, Colegiados, TFJA, PRODECON) por tema, lo obligatorio primero, sólo vigentes y con su cita formal. Ej.: «la orden de visita debe precisar su objeto». consulta es el tema en palabras (3 a 6 palabras rinden mejor; no un número de tesis). Dice si puede haber más (limite, hasta 10). Léalos con leer_precedente antes de citarlos. Por número o registro: vigencia_de_un_criterio o leer_precedente; por artículo: precedentes_de_un_articulo. Búsqueda por texto (sin vectores ni reordenador): una consulta que no está en español no se busca y se dice cómo pedirla. [EN: Search Mexican case law.]

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": {
      "consulta": "<consulta>"
    },
    "name": "buscar_jurisprudencia"
  }
}

Input Schema

NameRequiredDescriptionDefault
tiposNoSólo de estos tipos de documento.
limiteNoCuántos resultados (1 a 10; por omisión, 8).
fuentesNoSólo de estas fuentes: SJF (SCJN y tribunales federales), SCJN_SENTENCIAS, TFJA_SCTJ, PRODECON.
consultaYesEl tema en palabras, en español (3 a 6 palabras): «plazo para desvirtuar la presunción». No un número de tesis.
fecha_del_hechoNoCon ella, cada resultado dice si el texto que interpretó es el que rige ese día.
publicada_hastaNoSólo lo publicado hasta ese día.
solo_obligatoriaNotrue: sólo jurisprudencia y precedentes obligatorios.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / consulta / description
      Added value: +"El tema en palabras, en español (3 a 6 palabras): «plazo para desvirtuar la presunción». No un número de tesis."
    • addedInput schema / properties / fuentes / description
      Added value: +"Sólo de estas fuentes: SJF (SCJN y tribunales federales), SCJN_SENTENCIAS, TFJA_SCTJ, PRODECON."
    • addedInput schema / properties / limite / description
      Added value: +"Cuántos resultados (1 a 10; por omisión, 8)."
    • addedInput schema / properties / solo_obligatoria / description
      Added value: +"true: sólo jurisprudencia y precedentes obligatorios."
    • addedInput schema / properties / tipos / description
      Added value: +"Sólo de estos tipos de documento."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses result ordering ('lo obligatorio primero'), filtering ('sólo vigentes'), that results come with formal citation, that the engine is plain text with no vectors or reranker, and that a non-Spanish query is silently not searched unless rephrased. That is the kind of behavioral context annotations cannot carry.

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?

Front-loaded with the core purpose and example query, then sibling routing, in a compact paragraph with no filler. The clause chain (example, follow-up rule, routing, engine caveat) is dense but each element is actionable; only the appended English tag borders on redundant.

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?

Seven parameters, no output schema, and no contradictions: the description covers query construction, result ordering, citation obligation, verification workflow via leer_precedente, and the language precondition. Nothing an agent needs in order to call 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 coverage is 100%, so tipos, fuentes, limite, and the date parameters are already documented, making 3 the baseline. The description adds only practical advice for `consulta` (word count, not a tesis number) and a restatement of `limite`'s ceiling; it says nothing extra about fecha_del_hecho or solo_obligatoria semantics.

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?

States a specific verb and resource ('Busca precedentes mexicanos') plus scope (courts covered, only vigentes, with formal citation), and routes readers to leer_precedente to inspect results. An agent can distinguish it from precedentes_de_un_articulo or vigencia_de_un_criterio without opening any schema.

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?

Explicit when-to-use alternatives are named with their selecting condition: by number/registro use vigencia_de_un_criterio or leer_precedente, by article use precedentes_de_un_articulo. It also gives the recommended query shape ('3 a 6 palabras; no un número de tesis') and a mandatory follow-up ('Léalos con leer_precedente antes de citarlos').

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources