Skip to main content
Glama

Préparer la réservation

start_booking
Read-onlyIdempotent

Prepares a booking without creating it: re-checks the slot against live capacity and the basket against the centre, then returns bookingUrl — a washlib.com link that opens the booking form at the contact step with the centre, day, slot, vehicle and services pre-filled — with arrival times and the online / on-site totals. The booking exists only once the customer confirms their phone by SMS and pays, or chooses on-site payment, on Washlib. bookingUrl works only exactly as returned: an altered link loses the pre-fill.

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": {
      "centerSlug": "<centerSlug>",
      "vehicleType": "<vehicleType>",
      "serviceIds": "<serviceIds>",
      "date": "<date>",
      "timeSlot": "<timeSlot>"
    },
    "name": "start_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesChosen day, YYYY-MM-DD (Europe/Paris)
timeSlotYes
centerSlugYesCentre slug as returned by find_centers or search_available_slots
serviceIdsYesThe basket quote_booking priced: one formule, plus options
vehicleTypeYesvehicleTypes.value from get_center_details (s, m, l, xl, van, moto) — never the label.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / vehicleType / description
      Previous value: -"vehicleTypes.value from get_center_details (s, m, l, xl, moto) — never the label."New value: +"vehicleTypes.value from get_center_details (s, m, l, xl, van, moto) — never the label."
    • changedInput schema / properties / vehicleType / enum
      Previous value: -[
      -  "s",
      -  "m",
      -  "l",
      -  "xl",
      -  "moto"
      -]New value: +[
      +  "s",
      +  "m",
      +  "l",
      +  "xl",
      +  "van",
      +  "moto"
      +]
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotent, and the description is consistent with them while adding real context: the slot is re-checked against live capacity, the basket against the centre, and the booking is only real after SMS verification plus payment. The operational warning that bookingUrl works 'only exactly as returned' and loses its pre-fill if altered is exactly the kind of edge-case behavior annotations cannot 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?

Front-loaded with the core distinction (prepare, don't create) and then the return payload. The middle sentence is long and stacked with clauses about the URL, arrival times and totals, but every element earns its place; only minor tightening would improve readability.

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?

With no output schema, the description carries the return-value burden and does so thoroughly (bookingUrl, arrival times, online/on-site totals). What is missing is failure behavior — what happens or is returned when the live capacity re-check fails for the requested slot.

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 80% and the schema already documents centerSlug, date, serviceIds and vehicleType in detail, so the baseline of 3 applies. The description only restates that the centre, day, slot, vehicle and services get pre-filled, adding no new format or constraint information beyond the schema.

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 plus a negative scope — 'Prepares a booking without creating it' — which immediately separates it from a create/get booking tool. It also names the concrete output (bookingUrl) and the pre-fill contents, so an agent knows exactly what this call produces.

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?

'without creating it' plus the description of when the booking actually comes into existence (customer SMS confirmation and payment, or on-site payment) tells the agent this is the pre-checkout step. It does not explicitly name alternatives such as quote_booking or search_available_slots as prerequisites, so the routing is implied rather than spelled out.

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