Skip to main content
Glama

Alina Szaputko — Online Consultation Booking

Create a client-authorised Stripe checkout session

create_checkout_session
Idempotent

Creates a temporary booking hold and Stripe Checkout session; it does NOT confirm an appointment. Invoke only after request_client_consent has sent the client an email, the client has opened the confirmation page, reviewed the exact booking details, rules and privacy notice, and personally confirmed. The client must provide the resulting one-time consentToken. The token is short-lived, bound to the exact booking details and consumed once. Collect no clinical history or reason for therapy. The client enters payment details directly on Stripe; never ask for card data. Reuse the same requestId for retries of the same attempt. Enabled only when the deployment has an explicitly configured Preview test gate or Production live-booking gate. Preview test bookings are marked [TEST]; Production requires explicit live-mode acknowledgement and a Stripe live key. After payment, call get_agent_booking_status and confirm only when paid=true AND confirmed=true.

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": {
      "name": "<name>",
      "email": "<email>",
      "date": "<date>",
      "time": "<time>",
      "consultationLanguage": "<consultationLanguage>",
      "consentToken": "<consentToken>",
      "requestId": "<requestId>"
    },
    "name": "create_checkout_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYes
nameYes
timeYes
emailYes
phoneNo
requestIdYes
consentTokenYes
interfaceLanguageNo
consultationLanguageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare the generic profile (not read-only, not destructive, idempotent, open-world); the description adds the operationally decisive facts: the token is short-lived, bound to the exact booking details and single-use, the requestId must be reused on retries of the same attempt, and the tool is only enabled behind a configured Preview or Production gate with live-mode acknowledgement. It also discloses data-handling constraints (no clinical history, never solicit card data, payment entered on Stripe) that no annotation conveys.

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?

The key distinction and the preconditions are front-loaded, and each sentence carries an operational rule rather than filler. It is dense and long, but the density is justified by the mutation-plus-payment risk; only the ordering of the gating sentence after the data-handling rules feels slightly less than optimal.

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 9-parameter, open-world, payment-related mutation with no output schema, the description covers authorization, idempotency, environment gating, and the required follow-up call. The remaining gap is that it never says what the tool returns (presumably a checkout URL and hold expiry) or what happens on hold failure, which an agent needs when there is no output schema to consult.

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 0%, so the description carries the burden, and it does add real meaning for the two non-obvious parameters: consentToken provenance/lifetime/one-time consumption and requestId reuse for retries. However, six parameters (name, email, date, time, phone, interfaceLanguage, consultationLanguage) receive no semantics at all, and the language fields' relationship to each other is unexplained, so compensation is partial rather than complete.

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 two concrete resources ('creates a temporary booking hold and Stripe Checkout session') and immediately negates the closest misreading ('it does NOT confirm an appointment'), which cleanly separates it from get_agent_booking_status.

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 an explicit precondition chain (only after request_client_consent emailed the client, the client reviewed details and personally confirmed, and a consentToken exists) plus a post-condition handoff ('After payment, call get_agent_booking_status'). It also names the exact conditions for confirming (paid=true AND confirmed=true), so the agent knows both when to use this tool and when not to treat its success as a booking.

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