Skip to main content
Glama

Babelii-Diofis Account

Siapkan pesanan (belum dibayar)

prepare_purchase

Prepare an expiring, actor-bound intent without placing an order or debiting money. For products that need an inquiry this call runs the inquiry itself (no separate inquire_purchase needed). For identities WITHOUT an account (anonymous agents) buyer_name is REQUIRED; buyer_phone and buyer_email are optional and must never be demanded from the user. An account-bound identity buys as its account and needs none of them. An anonymous order is paid through the payment link returned by execute_purchase: give that link to the buyer and tell them fulfilment starts after payment. Show the returned destination, customer name (if any), product and amount to the user. Products with open_denom need amount (nominal typed by the buyer, min 1000); products with needs_inquiry need the inquiry_id returned by inquire_purchase for the same destination and amount. Fixed-price products in some groups return their native checkout form. The result carries a policy block: how long the intent is valid (expires_at, about 5 minutes), how many renewals remain, and the per-order and hourly limits of this identity. An order refused for a limit is final: do not split it, retry it or look for a way around it; tell the buyer plainly.

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_ref": "<product_ref>"
    },
    "name": "prepare_purchase"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountNo
buyer_nameNo
inquiry_idNo
buyer_emailNo
buyer_phoneNo
destinationNo
product_refYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description adds the substantive behavior: intents expire in about 5 minutes and are actor-bound, no money moves and no order is placed, renewals and per-order/hourly limits come back in a policy block, and a limit refusal is final. It also discloses the anonymous-vs-account buying model and that fulfilment begins only after payment.

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 is front-loaded and no sentence is filler; every clause carries operational detail an agent would otherwise have to guess. It is dense and unbroken prose, so scanning is harder than it needs to be, but the information density justifies the length.

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 non-idempotent mutation that mints an expiring intent, the definition covers prerequisites, identity modes, conditional parameter requirements, the payment hand-off, and limit-refusal handling. Since an output schema exists, it correctly spends only one sentence on the policy block rather than duplicating return structure.

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

Parameters5/5

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

With 0% schema description coverage across 7 params, the description carries the full burden and succeeds: buyer_name is required only for accountless identities, buyer_phone/buyer_email are optional and must not be demanded, amount is needed for open-denom products with min 1000, inquiry_id is needed for needs_inquiry products and must match destination and amount, and destination/product_ref are contextualized through the display and inquiry-matching instructions.

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?

The opening sentence gives a precise verb and resource ('prepare an expiring, actor-bound intent') and immediately bounds it negatively ('without placing an order or debiting money'), which is exactly what separates it from execute_purchase. The description also distinguishes it from inquire_purchase by stating it runs the inquiry itself for inquiry products.

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?

It names the sibling it replaces in specific conditions ('for products that need an inquiry this call runs the inquiry itself; no separate inquire_purchase needed') and routes payment follow-through to execute_purchase. It also gives explicit when-not guidance ('do not split it, retry it or look for a way around it') for refused orders.

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.

Resources