BridgesAgents

Pedir orçamento

request_quote

Pede orçamento a uma loja: para item com preço sob consulta (priceType ON_REQUEST em get_offers) ou quantidade especial. Devolve confirmUrl: o CONSUMIDOR abre, informa nome, WhatsApp e e-mail (e o endereço, na entrega) e o pedido vai para a loja, que responde com os preços em até 5 dias. Acompanhe em get_quote: DRAFT (esperando o consumidor), REQUESTED (esperando a loja), ANSWERED (preços em items, total e validUntil), ACCEPTED (virou pedido: orderNumber; o consumidor segue no mesmo link), DECLINED (a loja não atende: closeReason), REJECTED ou EXPIRED. Mostre a resposta ao consumidor e, com a decisão dele, use respond_to_quote. Em details de cada item, descreva o que ele quer (medidas, cor, prazo). O link vale 72 horas para o consumidor confirmar e aparece só nesta resposta.

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": {
      "storeId": "<storeId>",
      "items": "<items>",
      "fulfillment": "<fulfillment>"
    },
    "name": "request_quote"
  }
}

Input Schema

Name	Required	Description
`note`	No	Observação para a loja
`items`	Yes	Itens: lista de {productId, quantity, details}
`storeId`	Yes	storeId da loja (de get_offers)
`postalCode`	No	CEP do consumidor (obrigatório na entrega, no envio e a domicílio)
`fulfillment`	Yes	'pickup', 'delivery', 'shipping', 'in_store' ou 'at_customer'
`externalReference`	No	Seu id para este orçamento (conversa ou usuário), até 100 caracteres

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With readOnlyHint=false and idempotentHint=false already declared, the description still adds a great deal: the call returns a confirmUrl the consumer must open, the link is valid only 72 hours and appears only in this response, and the store has up to 5 days to answer. This is unusually rich behavioral context. It stops short of stating that a repeat call with the same inputs creates a new quote, but the non-idempotent call pattern is clear enough.

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?

Purpose and trigger are front-loaded, and the dense single paragraph covers the return value and the full state machine without filler. It is long and packs the DRAFT/REQUESTED/ANSWERED/ACCEPTED/DECLINED/REJECTED/EXPIRED list inline, which makes it harder to scan than a short bulleted sequence would be.

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

Completeness5/5

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

For a mutation tool with no output schema, the description supplies the one thing an agent cannot infer: the return value (confirmUrl) and what to do with it, plus the status lifecycle for the follow-up call. Nothing an agent needs in order to call this correctly or explain the result to a consumer is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the parameter docs are already strong, but the description adds real semantics on items.details ('descreva o que ele quer (medidas, cor, prazo)') and ties storeId back to get_offers and postalCode to delivery. That guidance on how to fill a loosely typed field goes beyond the schema's labels.

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?

Opens with a specific verb+resource ('Pede orçamento a uma loja') and immediately narrows the scope to price-on-request items (priceType ON_REQUEST in get_offers) or special quantities. An agent can distinguish this from get_offers (browse prices), get_quote (read status) and respond_to_quote (act on an answer) without opening another 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?

States exactly when to fire it (priceType ON_REQUEST, special quantity) and routes the rest of the flow explicitly: track status in get_quote, present the store's answer, then act with respond_to_quote based on the consumer's decision. Alternatives and hand-offs are named rather than inferred.

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?