Skip to main content
Glama

Buy from any US store for the user (assisted purchase / personal shopper)

request_assisted_purchase

Buy-it-for-me: sends an Assisted Purchase request to the Global Shopaholics team, for when the user wants something from a US store (including stores that refuse foreign cards or addresses) shipped to them. GS checks price/availability, confirms the total with the customer by email, buys from the US store, and ships it. Nothing is charged by this tool and no payment happens in chat; GS emails an invoice. Legal items only. Only call after the user has confirmed product link(s), quantity, destination, name and email. Returns a reference id and next steps.

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": {
      "product_urls": "<product_urls>",
      "destination_country": "<destination_country>",
      "name": "<name>",
      "email": "<email>"
    },
    "name": "request_assisted_purchase"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesCustomer full name.
emailYesCustomer email; GS replies here.
notesNo
phoneNoOptional phone/WhatsApp with country code.
variantNoSize/color/model details.
quantityNo
budget_usdNoMax the customer wants to spend on items.
product_urlsYesProduct page URL(s) at US stores (http or https).
payment_methodNoPreferred payment method.
destination_cityNo
destination_countryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: nothing is charged by the tool, no payment happens in chat, GS verifies price/availability and emails the customer an invoice, and the tool returns a reference id plus next steps. This fills in the money/consent model that an openWorld, non-idempotent create-style call badly needs and that the annotations alone would not convey.

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?

Densely packed but front-loaded with the core purpose and the cost/no-payment caveat before the preconditions. Every sentence carries information, though the single-run-on paragraph would scan faster with the preconditions and restrictions separated out.

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 an 11-parameter, request-creating tool with no output schema, the description covers the workflow, the money/consent boundary, the legal restriction, and what is returned. Remaining gaps (what happens on rejected store/item, how budget overruns are handled, whether the request can be amended) are modest rather than disqualifying.

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?

With 64% schema description coverage, the baseline is 3. The description does signal which inputs must be pre-confirmed (product links, quantity, destination, name, email), reinforcing the required-parameter set, but it says nothing about budget_usd, variant, notes, phone, or payment_method, leaving roughly a third of the parameters to the schema alone.

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 ('sends an Assisted Purchase request to the Global Shopaholics team') and makes the trigger condition explicit ('when the user wants something from a US store, including stores that refuse foreign cards or addresses'). An agent can immediately tell this apart from quoting/cost-estimation siblings because the description frames it as an actual buy-for-me request rather than a price lookup.

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

Usage Guidelines4/5

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

Strong precondition guidance: 'Only call after the user has confirmed product link(s), quantity, destination, name and email' plus a restriction ('Legal items only'). It does not name sibling tools or say when to prefer estimate_landed_cost / request_shipment_quote instead, so an agent must infer the ordering itself.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.