Cambio Uruguay

Oportunidades de autos usados

find_car_opportunities

Read-onlyIdempotent

Autos pedidos por DEBAJO de su cohorte fija: mismo modelo, año, versión, motor y caja, con km dentro de max(20.000, 30 %). Cada oportunidad pasa por su ficha (activa, mismo precio, sin choque/recupero/deuda/chapa extranjera declarados). Trae brecha %, brecha conservadora, la muestra (n, vendedores, p25/mediana/p75) y comparables con link.

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": "find_car_opportunities"
  }
}

Input Schema

Name	Required	Description
`body`	No	Carrocería (rural = familiar).
`fuel`	No	Combustible.
`page`	No	Página de resultados, desde 1.
`sort`	No	gap = mayor brecha.
`tier`	No	strict = evidencia sólida, exploratory = para explorar.
`brand`	No	Marca: "Toyota".
`kmMax`	No	Kilómetros máximos, p. ej. 100000.
`limit`	No	Resultados a devolver (default 8).
`seller`	No	dealer = automotora, private = particular.
`yearMin`	No	Año mínimo, p. ej. 2015.
`department`	No	Departamento del aviso.
`priceMaxUsd`	No	Precio máximo en dólares.
`transmission`	No	Caja.
`maxLitersPer100Km`	No	Consumo máximo (litros cada 100 km).

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedOct 28, 2026
- changedInput schema / properties / body / description
```
Previous value: -"Carrocería: sedan, hatchback, suv, pickup, rural (familiar), furgon, monovolumen, coupe, cabriolet."New value: +"Carrocería (rural = familiar)."
```
- addedInput schema / properties / brand / description
```
Added value: +"Marca: \"Toyota\"."
```
- addedInput schema / properties / department / description
```
Added value: +"Departamento del aviso."
```
- addedInput schema / properties / fuel / description
```
Added value: +"Combustible."
```
- addedInput schema / properties / kmMax / description
```
Added value: +"Kilómetros máximos, p. ej. 100000."
```
- addedInput schema / properties / limit / description
```
Added value: +"Resultados a devolver (default 8)."
```
- addedInput schema / properties / page / description
```
Added value: +"Página de resultados, desde 1."
```
- addedInput schema / properties / sort / description
```
Added value: +"gap = mayor brecha."
```
- addedInput schema / properties / tier / description
```
Added value: +"strict = evidencia sólida, exploratory = para explorar."
```
- addedInput schema / properties / transmission / description
```
Added value: +"Caja."
```
- addedInput schema / properties / yearMin / description
```
Added value: +"Año mínimo, p. ej. 2015."
```
AddedSep 21, 2026

TDQS

A3.7/5.0

Behavior5/5

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

Despite annotations covering read-only and non-destructive behavior, the description adds substantial methodological detail: the fixed cohort definition, mileage tolerance formula, listing validation checks (active, same price, no declared accident/repo/debt/foreign bodywork), and the returned metrics. This gives the agent a clear picture of what makes a result and what the tool computes beyond a simple search.

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?

The description is dense but front-loaded: it first defines the core opportunity condition, then the validation criteria, then the return contents. Three sentences carry a lot of information with little waste, though the jargon-heavy phrasing may require domain familiarity.

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 14-parameter tool with no output schema, the description does a good job explaining methodology and named return values such as gap percentage, conservative gap, sample statistics and comparables. It stops short of explaining pagination or trade-offs between strict/exploratory tiers, but the schema covers those details.

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 parameters are already fully documented. The description mentions cohort dimensions and output fields but does not add parameter-level meaning beyond the schema, which is acceptable given the high coverage 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?

The description states a specific purpose: listing used cars priced below a fixed cohort defined by model, year, version, engine, transmission and mileage tolerance. It is clear enough to distinguish from general search, but it does not explicitly name or differentiate from siblings like search_used_cars or car_model_prices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives such as search_used_cars, car_model_prices, or car_market_report. The intended use as a bargain-finder is implied, but no conditions, exclusions, or alternative routing are provided.

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

All Cambio Uruguay tools Inspect

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.