Skip to main content
Glama

huggingface_search_dataset

Read-only

Search a public Hugging Face dataset for Chilean jurisprudence and doctrine, retrieving exact case, norm or entity matches with official citations and revision-pinned links.

Instructions

Consulta el repositorio público oficial en Hugging Face Datasets Hub (pablobenavidesj/doctrina-jurisprudencia-chile) y recupera contexto y enlaces directos con citas oficiales. Con el mapa del corpus busca primero lo exacto (rol, norma o entidad: la ficha y quién la cita) y cita con la URL fijada a la revisión del dataset.

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": {
      "query": "<query>"
    },
    "name": "huggingface_search_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
rolNoRol exacto de una causa (ej. '10641-2024' de la Corte Suprema, '2402-12-INA' del TC, 'R-21-2021' ambiental): trae su ficha y los documentos que la citan (opcional)
limitNoNúmero máximo de archivos o recursos a devolver (por defecto 5)
normaNoNorma citada (ej. 'art. 1545 del Código Civil', 'Ley 19.300'): los documentos del dataset que la citan (opcional)
queryYesTérmino de búsqueda doctrinal o institucional (ej. 'responsabilidad', 'despido', 'contratos')
entidadNoMinistro, autor, revista, sala o recurso, por nombre o ID del mapa (ej. 'María Gajardo Harboe', 'revista:rchd'): los documentos vinculados (opcional)
coleccionNoAcota a una colección: 'cs' (Corte Suprema), 'tc', 'ta' (tribunales ambientales), 'doc' (doctrina y revistas), 'guia', 'bib' o 'pub' (opcional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.14.0
    • addedInput schema / properties / coleccion
      Added value: +{
      +  "description": "Acota a una colección: 'cs' (Corte Suprema), 'tc', 'ta' (tribunales ambientales), 'doc' (doctrina y revistas), 'guia', 'bib' o 'pub' (opcional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / entidad
      Added value: +{
      +  "description": "Ministro, autor, revista, sala o recurso, por nombre o ID del mapa (ej. 'María Gajardo Harboe', 'revista:rchd'): los documentos vinculados (opcional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / norma
      Added value: +{
      +  "description": "Norma citada (ej. 'art. 1545 del Código Civil', 'Ley 19.300'): los documentos del dataset que la citan (opcional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / rol
      Added value: +{
      +  "description": "Rol exacto de una causa (ej. '10641-2024' de la Corte Suprema, '2402-12-INA' del TC, 'R-21-2021' ambiental): trae su ficha y los documentos que la citan (opcional)",
      +  "type": "string"
      +}
  2. Addedv1.6.5

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnly, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuine value beyond that: results are direct links with official citations, and URLs are pinned to a specific dataset revision, which tells the agent the references are stable and citable. It does not mention result ordering, pagination, or what happens when a 'rol' has no ficha.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

It is short, two sentences, and front-loads the repository, which is good. However, the second sentence is a run-on with nested parentheticals that mixes search strategy, return content, and URL-revision advice, making it slower to parse than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter search tool with no output schema, the description covers the source and the citable-link outcome but says little about the shape of results (fields per hit, whether ficha and citing-documents are separate sections, ordering). The 'mapa del corpus' phrase hints at an internal index structure that is never explained, leaving a conceptual gap.

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 description coverage is 100%, so the schema already explains rol, norma, entidad, coleccion, limit, and query. The description reinforces the intended lookup order (rol/norma/entidad first, each yielding 'la ficha y quién la cita') but that semantic is already present in the schema's parameter descriptions, so it adds little beyond the baseline.

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?

States a specific verb and resource: it queries the public Hugging Face Datasets Hub repository named 'pablobenavidesj/doctrina-jurisprudencia-chile' and returns context plus direct citation links. The purpose is concrete, but the description never distinguishes this corpus from closely named siblings like doctrina_search, pjud_search_jurisprudencia, or ambiental_buscar_jurisprudencia, so an agent cannot tell which to prefer from the text alone.

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?

Offers one procedural hint — 'busca primero lo exacto (rol, norma o entidad)' — which implies trying exact identifiers before free-text terms. There is no explicit when-not guidance and no named alternative for doctrinal or jurisprudential lookups covered by sibling tools, so selection between tools is left to inference.

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

Deploy Server

Other Tools