Skip to main content
Glama
Sign In

Cambio Uruguay

by io.github.eduair94
OverviewDiscussionsAdmin

Buscar productos y precios en Uruguay

search_products
Read-onlyIdempotent

Búsqueda unificada en los directorios de productos, relevados a diario en tiendas uruguayas, Mercado Libre y Facebook Marketplace: celulares (modelo + almacenamiento, precio nuevo más bajo), sillas de escritorio y gamer (con calificación), hogar (38 categorías para equipar una casa: heladera, lavarropas, colchón, cocina, aire acondicionado, TV…, con banda de precio nuevo y usado) y movilidad eléctrica (monopatines, bicicletas eléctricas). Devuelve el precio más bajo con vendedor y link, la banda típica (p25–mediana–p75), cuánto ahorra comprar usado y la ficha del sitio. Ordena del más barato al más caro.

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": "search_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoPalabras a buscar: "heladera no frost", "iphone 13", "silla ergonómica".
brandNoMarca: "Samsung", "Midea".
limitNoResultados a devolver (default 12).
verticalNoDirectorio (default: todas).
conditionNoused = sólo con banda de usados, al precio usado.
maxPriceUyuNoPrecio máximo en pesos.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / brand / description
      Added value: +"Marca: \"Samsung\", \"Midea\"."
    • addedInput schema / properties / limit / description
      Added value: +"Resultados a devolver (default 12)."
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description goes further by disclosing data provenance ('relevados a diario', tiendas uruguayas, Mercado Libre, Facebook Marketplace), what each result contains (lowest price with seller and link, p25–mediana–p75 band, used-vs-new savings, site ficha) and the sort order. With no output schema, this carries the return-value burden well.

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 a single dense sentence that front-loads sources and coverage before moving to outputs and ordering, so every clause is relevant. The nested parentheses and the ellipsis in the hogar category list make it slightly harder to parse than it needs to be.

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

Completeness4/5

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

For a 6-parameter, all-optional search tool with a fully documented schema and no output schema, the description covers sources, coverage, return fields and ordering. Minor gaps remain about what happens when 'todas' is combined with a narrow text query, or how results are truncated relative to the limit.

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 all six parameters, including both enums and the price ceiling, are already documented in the schema. The description restates the verticals and the new/used price band concept but adds no syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 ('búsqueda') and resource ('productos y precios') and then enumerates the covered verticals (celulares, sillas, hogar, movilidad eléctrica) with the exact attributes returned for each. An agent can immediately distinguish this from search_used_cars, supermarket_prices or search_rentals because the catalog scope is spelled out.

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?

The enumeration of verticals implicitly tells the agent what the tool covers, so usage can be inferred. However, there is no explicit routing guidance (e.g. 'para autos usá search_used_cars' or 'para precios de supermercado usá supermarket_prices'), and no note about when this unified search is preferable to a sibling.

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

All Cambio Uruguay toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources