Skip to main content
Glama

cgr_search_jurisprudencia

Read-only

Search binding CGR administrative jurisprudence and analyze individual or batch dicta by legal term, topic, or doc ID; optionally download official PDFs and convert to Markdown for graph ingestion.

Instructions

Busca dictámenes vinculantes en la jurisprudencia administrativa de la Contraloría General de la República (CGR). Permite buscar por término o analizar dictámenes individuales o en lote (doc_id/doc_ids), descargar PDF oficial firmado, convertir a Markdown canónico, ingestar en LegalGraphify y desglosar consideraciones relevantes por tema.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cgr_search_jurisprudencia"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoTérmino de búsqueda jurídica (ej. 'confianza legitima contrata', 'probidad')
doc_idNoCódigo de dictamen CGR a analizar a fondo, con su año (ej. 'E311060N23', 'D286N26' o '49495/2009'); si el número sin año corresponde a varios dictámenes se devuelven los candidatos
doc_idsNoLista de códigos de dictámenes CGR para análisis en lote
tema_relevanteNoPunto de derecho o tema controvertido para rankear y citar consideraciones específicas
descargar_formatoNoDescargar el PDF oficial firmado desde la CGR ('pdf')
convertir_a_md_y_graficarNoConvierte a Markdown canónico e ingesta en el grafo LegalGraphify

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.14.0
    • addedInput schema / properties / convertir_a_md_y_graficar
      Added value: +{
      +  "default": false,
      +  "description": "Convierte a Markdown canónico e ingesta en el grafo LegalGraphify",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / descargar_formato
      Added value: +{
      +  "description": "Descargar el PDF oficial firmado desde la CGR ('pdf')",
      +  "enum": [
      +    "pdf"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / doc_id
      Added value: +{
      +  "description": "Código de dictamen CGR a analizar a fondo, con su año (ej. 'E311060N23', 'D286N26' o '49495/2009'); si el número sin año corresponde a varios dictámenes se devuelven los candidatos",
      +  "type": "string"
      +}
    • addedInput schema / properties / doc_ids
      Added value: +{
      +  "description": "Lista de códigos de dictámenes CGR para análisis en lote",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / tema_relevante
      Added value: +{
      +  "description": "Punto de derecho o tema controvertido para rankear y citar consideraciones específicas",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "query"
      -]
  2. First observedv1.5.1

TDQS

B3.2/5.0
Behavior2/5

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

The description discloses several behaviours beyond the annotations (downloading the official signed PDF, producing canonical Markdown, breaking down considerations by topic), which is useful. However, it states that the tool can 'ingestar en el grafo LegalGraphify', i.e. write into a persistent graph, while the annotations declare readOnlyHint=true — a substantive conflict for that optional mode. It also omits result volumes, pagination, and cost/latency implications of batch analysis.

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?

Two sentences, front-loaded with purpose and followed by a compact capability list; nothing is padded or redundant. The second sentence is dense but each clause maps to a distinct mode, so it earns its length.

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, zero-required multi-mode tool with no output schema, the description covers the available modes but says nothing about what results look like, how ambiguous doc_id resolution is surfaced, or what happens on failures in batch mode. It is adequate to pick the tool but thin for predicting its behaviour.

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 parameters are already documented with examples and defaults, and 3 is the baseline. The description adds only a loose mapping between modes and parameters ('por término', 'individuales o en lote', 'por tema') without clarifying interaction rules, such as whether query and doc_ids can be combined or what tema_relevante does when doc_id is absent.

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 opens with a specific verb and resource: searching binding opinions ('dictámenes vinculantes') in the CGR's administrative jurisprudence, which scopes it clearly against judicial-branch siblings. It then enumerates the additional capabilities (batch analysis, PDF download, Markdown conversion, graph ingestion, topical breakdown), so an agent knows what the tool covers. It does not explicitly contrast itself with sibling search tools, which keeps it from a 5.

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?

Usage is implied by the mode list: search by term vs. analyze one dictamen (doc_id) vs. batch (doc_ids) vs. graph ingestion. There is no explicit statement of when to prefer this tool over alternatives, no preconditions, and no guidance on combining modes or on when NOT to use the ingestion flag.

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