Radar ML

Informe de oportunidad

informe_oportunidad

Analiza si conviene vender un producto en Mercado Libre: precio de mercado, nivel de competencia, ventana de precio recomendada, margen estimado (si se pasa el costo) y un veredicto 'entrar / entrar con cuidado / no entrar' con sus motivos. Precio: USD 1.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "producto": "<producto>"
    },
    "name": "informe_oportunidad"
  }
}

Input Schema

Name	Required	Description	Default
`pais`	No	País: AR, MX, BR, CL, CO o UY	AR
`producto`	Yes	Producto a analizar, por ejemplo 'mate térmico'
`costo_envio`	No	Costo de envío por unidad que paga el vendedor, en moneda local (0 si lo paga el comprador)
`comision_pct`	No	Comisión + cuotas + costos de venta en %, por defecto 20
`costo_unitario`	No	Costo por unidad puesto en destino, en moneda local

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A3.7/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full burden; it does disclose the paid nature (USD 1), the verdict categories, and the conditional rule that margin is only computed when the cost is supplied. It does not state the safety profile (read-only vs mutation), latency, rate limits or whether repeated identical calls are billed again, which for an unannotated paid tool is a real gap.

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?

A single dense sentence that front-loads the verb and question, followed by the price tag. Every clause maps to a real output, though the embedded comma-separated enumeration is slightly harder to scan than a short bulleted list would 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?

With five parameters and no output schema, the description usefully spells out what the report contains and its verdict taxonomy, which is exactly the missing structured information. It falls short on what happens with thin or missing market data and on the concrete shape/units of the returned figures.

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 baseline is 3. The description adds only one semantic link beyond the schema: margin is produced only 'si se pasa el costo', tying costo_unitario to an output, but it says nothing about the role of pais, comision_pct or costo_envio beyond what the schema already documents.

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 ('Analiza si conviene vender') on a specific resource (a product on Mercado Libre) and enumerates the concrete outputs: market price, competition, price window, estimated margin and a verdict. That enumeration also implicitly separates it from the lighter sibling precio_de_mercado, which delivers only one of those components.

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 framing 'si conviene vender un producto' implies the use case (sourcing/listing decisions), but there is no explicit when-to-use vs when-not guidance and no sibling is named as an alternative. The cost line ('Precio: USD 1') is a useful purchasing signal but not usage guidance.

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

All Radar ML 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.

Resources

Need Help?