BridgesAgents

Buscar produtos

search_products

Read-onlyIdempotent

Busca produtos de qualquer segmento de varejo pelo nome ou marca (ex.: 'arroz 5kg', 'fone bluetooth'). Ignora acentos. Devolve o id de cada produto para consultar ofertas em get_offers. Para resultados que o consumidor consegue receber ou retirar, informe a localização: latitude e longitude (mais preciso) e/ou o CEP. Com localização, só vêm produtos que alguma loja entrega ali ou deixa retirar por perto. radiusKm limita às lojas até essa distância do consumidor (ex.: postos num raio de 5 km, para acompanhar o preço da gasolina). adult=true: produto para maiores de 18 (bebida alcoólica, tabaco); cabe a você confirmar a idade com o consumidor. inStoreOnly=true: vendido só no local (combustível), sem carrinho. kind: GOOD (produto físico), FUEL (combustível), SERVICE (serviço), BOOKABLE (viagem, reserva), DIGITAL (curso, gift card), RENTAL (aluguel por período: create_cart com startDate e endDate) PROPERTY (imóvel: não se compra, marca-se visita; para buscar imóvel com filtros, use search_properties) ou VEHICLE (carro, moto: não se compra, marca-se visita ou test drive na loja; para buscar com filtros, use search_vehicles); attributes traz os dados do tipo (duration_minutes, max_guests, color, size, weight_kg...). variants: as variações do mesmo item (cor, tamanho, voltagem), cada uma com o próprio id; pergunte qual o consumidor quer e use o id dela em get_offers e create_cart.

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": {
      "query": "<query>"
    },
    "name": "search_products"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Máximo de resultados (1 a 50)
`query`	Yes	Texto da busca, em português
`country`	No	País do consumidor, código de 2 letras (ex.: BR, US, PT). Padrão: BR
`latitude`	No	Latitude do consumidor
`radiusKm`	No	Só lojas até esta distância do consumidor, em km (0 a 100). Exige localização
`longitude`	No	Longitude do consumidor
`postalCode`	No	Código postal do consumidor (no Brasil, o CEP: ex.: 30140-010). De outro país, informe também country

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, yet the description still adds real operational detail: accent-insensitive matching, that location filters to products some store delivers or allows pickup nearby, and that radiusKm constrains stores rather than products. However, it introduces parameter-like flags (adult, inStoreOnly, kind) that are not in the input schema, which muddies the actual call contract.

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?

It is front-loaded with the purpose and example, which is good, but the body is a single dense run-on stitched together with semicolons, and the long kind enumeration plus variant paragraph bloats it. Substantial content is useful, but the structure makes it easy to miss the actual callable parameters.

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 no output schema, describing that each product carries an id, type-specific attributes and variants is genuinely necessary, and the description delivers it along with the get_offers next step. Gaps remain: no mention of limit/pagination behavior or result ordering, and the non-schema parameters may lead an agent to build an invalid call.

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, and the description only adds modest meaning for radiusKm and the latitude/postalCode precision trade-off. Worse, it discusses adult, inStoreOnly, kind, attributes and variants as if they were inputs, none of which exist in the schema (additionalProperties=false), creating a false impression of available filters.

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 produtos ... pelo nome ou marca') plus scope ('qualquer segmento de varejo') and an example query. It explicitly routes property and vehicle searches to search_properties and search_vehicles, so an agent can separate it from those siblings 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 Guidelines5/5

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

Gives concrete when-to-use guidance: supply latitude/longitude and/or postal code for receivable results, radiusKm for distance-bounded store sets (with a petrol-price example), and explicit handoffs to get_offers, create_cart, search_properties and search_vehicles. It also assigns the agent a responsibility for adult=true (confirming age) and tells it to ask the consumer which variant they want.

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

All BridgesAgents 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?