Skip to main content
Glama

Request a car booking

request_booking

Files a car rental request in North Cyprus for a person who has agreed to the car, dates, places, extras and total, using their own name, email and phone. The Kipra team confirms the request; until then it is not a confirmed booking. No payment is taken. An email asks the person for a photo of their driving licence and ID card or passport. A second driver is added on the booking page.

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": {
      "car_id": "<car_id>",
      "pickup_at": "<pickup_at>",
      "return_at": "<return_at>",
      "full_name": "<full_name>",
      "email": "<email>",
      "phone": "<phone>",
      "expected_total_eur": "<expected_total_eur>"
    },
    "name": "request_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailYesWhere the booking details and document link are sent.
phoneYesPhone in international format, for example +905551112233.
addonsNoExtras charged per day.
car_idYescar_id of the chosen car.
currencyNoCurrency the person wants to see and pay in.
languageNoLanguage of the result and the booking link: 'tr' for Turkish, otherwise 'en'.en
full_nameYesThe person's full name.
pickup_atYesPickup date-time 'YYYY-MM-DDTHH:mm', Cyprus local time, within the booking hours.
return_atYesReturn date-time 'YYYY-MM-DDTHH:mm', after pickup_at, within the booking hours.
validate_onlyNotrue = run every check and file nothing: no request is created and no email is sent.
pickup_locationNoWhere the car is handed over.
return_locationNoWhere the car comes back.
expected_total_eurYesThe total the person agreed to. A different current total is refused.

Output Schema

NameRequiredDescriptionDefault
statusYes
referenceNo
total_eurYes
next_stepsYes
already_requestedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / addons / items / enum
      Previous value: -[
      -  "child_seat",
      -  "wifi",
      -  "casco",
      -  "tire_ins",
      -  "young_driver"
      -]New value: +[
      +  "child_seat",
      +  "casco",
      +  "tire_ins",
      +  "young_driver"
      +]
  2. Changed4 schema fields changed
    • addedInput schema / properties / validate_only
      Added value: +{
      +  "description": "true = run every check and file nothing: no request is created and no email is sent.",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / status / const
      Removed value: -"request_received"
    • addedOutput schema / properties / status / enum
      Added value: +[
      +  "request_received",
      +  "validated"
      +]
    • changedOutput schema / required
      Previous value: -[
      -  "status",
      -  "already_requested",
      -  "reference",
      -  "total_eur",
      -  "next_steps"
      -]New value: +[
      +  "status",
      +  "total_eur",
      +  "next_steps"
      +]
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the outbound side effect (an email requesting a licence photo and ID/passport), that no payment is taken, that the booking stays unconfirmed until the Kipra team approves it, and that a second driver is handled separately on the booking page. None of that is derivable from readOnlyHint=false or openWorldHint=true, and it is consistent with them.

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 action, then successive sentences cover confirmation state, payment, email follow-up and second drivers — all useful. The closing sentence about the second driver on the booking page is slightly tangential since this tool cannot add one, costing a point.

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 13-parameter mutation tool this covers the lifecycle well (filed → pending → confirmed, no payment, document email), and the output schema handles return values. The notable gap is duplicate behavior: idempotentHint=false means a retry files a second request, but the description never warns about that.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds a real constraint by tying name, email and phone to 'their own' identity and by reiterating that the agreed total is what gets filed. It does not explain validate_only or the currency/language knobs beyond the schema, so it stops short of a 5.

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 — 'Files a car rental request in North Cyprus' — for a person who has already agreed to car, dates, places, extras and total. That framing cleanly separates it from read-only siblings like check_car_availability or list_prices, and the 'request, not confirmed booking' distinction prevents misreading it as a reservation tool.

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?

The precondition for use is explicit: the person must already have agreed to the car, dates, places, extras and total, and must book under their own name, email and phone. It does not name alternatives or state when NOT to use it (e.g. availability still unverified), so exclusions are left implicit.

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