Skip to main content
Glama

sii_search_circulares

Read-only

Search official SII circulars and Director instructions by number or tax subject, with tolerant matching, batch analysis, PDF download, Markdown conversion, and LegalGraphify ingestion.

Instructions

Busca circulares e instrucciones oficiales del Director del Servicio de Impuestos Internos (SII) por número o por la materia del índice oficial (no distingue tildes, plural ni orden de las palabras). Para leer el texto íntegro de un acto, usar sii_leer_documento. Permite buscar por término o analizar circulares en lote/individuales, descargar PDF oficial, convertir a Markdown canónico, ingestar en LegalGraphify y desglosar instrucciones 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": "sii_search_circulares"
  }
}

Input Schema

NameRequiredDescriptionDefault
aniosNoAños a consultar (por defecto, los últimos siete)
queryNoMateria tributaria o año (ej. 'iva servicios', 'gasto tributario', '2024')
numeroNoNúmero de circular a analizar (ej. '45', '35')
numerosNoLista de circulares para análisis en lote
tema_relevanteNoTema tributario controvertido para rankear y citar la instrucción pertinente
descargar_formatoNoDescargar el PDF oficial de la circular ('pdf')
convertir_a_md_y_graficarNoConvierte a Markdown canónico e ingesta en LegalGraphify

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.14.0
    • addedInput schema / properties / anios
      Added value: +{
      +  "description": "Años a consultar (por defecto, los últimos siete)",
      +  "items": {
      +    "type": "integer"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / convertir_a_md_y_graficar
      Added value: +{
      +  "default": false,
      +  "description": "Convierte a Markdown canónico e ingesta en LegalGraphify",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / descargar_formato
      Added value: +{
      +  "description": "Descargar el PDF oficial de la circular ('pdf')",
      +  "enum": [
      +    "pdf"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / numero
      Added value: +{
      +  "description": "Número de circular a analizar (ej. '45', '35')",
      +  "type": "string"
      +}
    • addedInput schema / properties / numeros
      Added value: +{
      +  "description": "Lista de circulares para análisis en lote",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / tema_relevante
      Added value: +{
      +  "description": "Tema tributario controvertido para rankear y citar la instrucción pertinente",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "query"
      -]
  2. First observedv1.5.1

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations it discloses matching behavior not visible anywhere in the schema (no distinción de tildes, plural ni orden de palabras) and, importantly, that a parameter can write to an external system ("ingestar en LegalGraphify"), a side effect the readOnlyHint would otherwise hide. It still says nothing about result volume, pagination, or failure behavior on unmatched numbers.

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?

The first two sentences are front-loaded and efficient: purpose, matching rules, then the alternative tool. The third sentence is a six-item capability list strung together with commas, mixing search, download, conversion, ingestion and breakdown without structure, which dilutes the routing signal.

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 tool with seven optional parameters, zero required parameters and no output schema, the description covers the input modes but never states what a call with no arguments returns, what the results look like, or how batch versus single results differ. Adequate to invoke, insufficient to predict the response shape.

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 the schema already documents all seven parameters; the description mostly restates them in prose (término, número, lote, PDF, Markdown/ingesta). The one genuine addition is the query-matching semantics (accent/plural/word-order insensitivity), which meaningfully informs how the 'query' and 'tema_relevante' parameters behave, but the rest is redundant with the schema.

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 circulares e instrucciones oficiales del Director del SII") and immediately scopes the retrieval axes: número o materia del índice oficial. It also names the sibling it is not (sii_leer_documento), so an agent can separate searching from full-text reading without opening either 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?

Explicit routing for the main alternative: "Para leer el texto íntegro de un acto, usar sii_leer_documento" gives a clear when-not-this condition. It also sketches several usage modes (búsqueda por término, análisis en lote/individual, descarga, conversión, ingestión), but it does not say when to choose one mode over another or what triggers batch vs. single analysis.

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