Skip to main content
Glama

Buscando sentencias

buscar_sentencias

Search full-text Peruvian Constitutional Court resolutions from both current and historical (2001-2018) inventories in one unified, deduplicated query.

Instructions

Busca en el TEXTO COMPLETO de TODAS las resoluciones del Tribunal Constitucional, COMBINANDO los dos inventarios del TC en una sola vista: (a) la sistematizacion actual (indice Elasticsearch del portal, hasta 2026) y (b) el inventario historico de resoluciones (2001-2018). El server QUITA TILDES del texto (el indice NO matchea acentos) y fusiona las filas con dedup de documento.

Args: search: texto a buscar en el contenido del fallo (multi-palabra si funciona en el motor historico; el comodin '' tambien: 'funcionarios'). Con total 0 prueba otra palabra clave o pasa a busqueda_avanzada. page: pagina 1-based (cap de 1000 paginas en ambos inventarios). modo: (inventario historico) 'todas' (contenga TODAS las palabras; default), 'algunas' (contenga ALGUNAS) o 'frase' (la frase completa).

Devuelve: {'ok', 'total' (suma de ambos inventarios), 'pagina', 'tamano_pagina' (variable: hasta 20 filas por bloque), 'paginas' (maximo entre inventarios), 'siguiente_pagina', 'filas': [{index GLOBAL, numero_expediente, numero_sentencia?, demandante, demandado, fecha_publicacion, fecha_sentencia?, fecha_ingreso?, sentido?, tipo?, distrito?, sala?, tesaurio?, slug?, url_pdf, extractos/texto}], 'ms', 'nota'?}: las filas del bloque primero vienen de la sistematizacion actual y luego del inventario historico; los documentos repetidos en ambos se omiten (dedup, declarado en 'nota'). El TEXTUAL para fichas completas: detalle_sentencia (si la fila trae 'slug').

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": {
      "search": "<search>"
    },
    "name": "buscar_sentencias"
  }
}

Input Schema

NameRequiredDescriptionDefault
modoNo
pageNo
searchYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and delivers: accent/tilde stripping so unmatched accents are explained, cross-inventory dedup of repeated documents surfaced in 'nota', block ordering (current index first, then historical), a 1000-page cap, and variable page size of up to 20 rows. These are non-obvious traits an agent could not infer from schema or annotations.

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?

It is long and dense, but front-loaded with purpose and then cleanly partitioned into Args and Devuelve sections, so every part earns its place. Slight verbosity in the return-value paragraph keeps it from a 5.

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?

For a tool merging two heterogeneous sources with an output schema present, the definition covers query syntax, pagination limits, dedup semantics, row ordering, and how to chain into detalle_sentencia. Nothing an agent needs 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.

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: 'search' explains multi-word behavior and the '*' wildcard, 'page' explains 1-based indexing and the 1000-page cap, and 'modo' supplies the effective enum ('todas'|'algunas'|'frase') that the schema's untyped anyOf string omits. This fully compensates for the coverage gap.

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 names a specific verb (Busca) and a precisely scoped resource: full text of ALL Tribunal Constitucional resolutions, explicitly clarifying that it merges the current systematization index and the historical inventory. It routes the agent away from the sibling busqueda_avanzada, so it is distinguishable 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 Guidelines4/5

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

It gives concrete fallback conditions: 'Con total 0 prueba otra palabra clave o pasa a busqueda_avanzada' and points to detalle_sentencia for full records when a 'slug' is present. Alternatives are named with conditions, though the other siblings (resultados_sistematizacion, resultados_tesauro, listar_*) are not contrasted.

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