Skip to main content
Glama

Pagetool

Charge the saved card

purchase_execute
DestructiveIdempotent

Charges the saved card of the customer immediately for a purchase they have explicitly agreed to in this conversation. Only call it after they have confirmed the exact item and amount in words - this tool moves real money right away. A refused or unchecked domain ending carries reason and a plain reason_text: unsupported or price_unavailable mean we do not sell that ending right now; lookup_failed or cap_reached mean it was NOT checked, so search again, and never tell the customer we do not sell it.

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": {
      "kind": "<kind>",
      "item": "<item>",
      "consent_confirmed": "<consent_confirmed>",
      "consent_item": "<consent_item>",
      "consent_amount_cents": "<consent_amount_cents>",
      "consent_statement": "<consent_statement>"
    },
    "name": "purchase_execute"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYesThe exact thing being bought; for kind='domain', the full domain name.
kindYesWhat is being bought. Only 'domain' is available in chat today.
consent_itemYesThe item the customer agreed to buy, as they understood it. If it does not match what is being charged, the charge is REFUSED.
consent_confirmedYesPass 'user_confirmed' ONLY after the customer has explicitly agreed to this exact purchase and amount in the conversation. Do not set it on your own initiative.
consent_statementYesThe customer's own words agreeing to this purchase, relayed verbatim. Must mention the item or the price. Do not invent it — if the customer has not explicitly agreed to this amount, do not call this tool.
consent_amount_centsYesThe exact amount in cents the customer agreed to pay. If it does not match the real server-side price, the charge is REFUSED and nothing happens.

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?

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds context the annotations cannot: money moves immediately, a mismatch on item or amount triggers a server-side REFUSAL with no charge, and the reason codes split into 'we do not sell this' vs 'this was never checked.' The instruction never to tell the customer an ending is unsupported on lookup_failed or cap_reached is genuinely operational detail no structured field carries.

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?

Two sentences, front-loaded with the charge action and the consent gate before the error-handling detail. The second sentence is dense and references `reason`/`reason_text` fields without setup, which reads slightly abruptly given there is no output schema, but every clause carries actionable content.

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 a six-required-parameter, irreversible money-moving tool, it covers the consent gate, the refusal conditions, and the correct follow-up action for each failure class — the critical gaps for safe invocation are closed. What is left out is the success response shape; with no output schema that would have been worth a sentence, since the description only describes the refusal branch.

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 each of the six parameters is already well documented, including the enum meanings for kind and consent_confirmed. The description reinforces the consent requirement ('in words', 'exact item and amount') but adds no new syntax, format, or constraint semantics beyond what the schema states. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Charges the saved card of the customer immediately for a purchase.' The immediacy plus the consent precondition makes the intent unmistakable, and it reads clearly differently from siblings like purchase_link or payment_status. It stops short of the 5 mark because it never names the alternative tools it is being compared against.

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?

Explicitly prescribes the precondition for calling ('Only call it after they have confirmed the exact item and amount in words') and explains the consequence of the alternative path — on a refused or unchecked ending, search again rather than declaring the item unsellable. It also gives the when-not implicitly through the consent gate, which is exactly the guidance an agent needs before moving money.

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