comparador-luz-gas
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| comparar_ofertasA | Consulta el comparador oficial de la CNMC y devuelve las ofertas de luz y/o gas ordenadas por precio, con un análisis a varios años (rotar de oferta, permanencias, precio fijo vs. por tramos). Basta el QR de una factura, o código postal + consumo anual. |
| leer_factura_qrA | Interpreta el QR de una factura de luz (ya decodificado): código postal, potencia, consumo por tramos del periodo y anual, fechas e importe. No consulta la CNMC. |
| leer_facturaA | Lee el QR de una factura de luz en PDF o imagen del disco local y devuelve sus datos. Necesita el extra |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
comparar_ofertas is clearly the query/comparison tool, but leer_factura and leer_factura_qr are two adjacent invoice-reading steps that an agent could confuse. The descriptions clarify the distinction (file on disk vs. already-decoded QR), preventing real overlap but leaving some boundary ambiguity.
All three tools use consistent Spanish snake_case verb_noun naming (comparar_ofertas, leer_factura, leer_factura_qr). The leer_factura / leer_factura_qr prefix pairing is a predictable, readable convention.
Three tools is slightly lean but appropriate for a narrow comparison/reading domain; each tool earns its place covering extract, read, and compare. It is on the lower edge but not problematically thin.
The surface covers a full workflow: read a PDF/image invoice, parse its QR, and compare offers. A minor gap is that leer_factura/leer_factura_qr mention only electricity invoices while comparar_ofertas handles gas too, but agents can still work around this.