Skip to main content
Glama

Request a booking

request_booking

Lodge a booking REQUEST for a private (not shared-shuttle) fixed-price Queensland route — Gold Coast / Brisbane airport or Brisbane Cruise Terminal, including Byron Bay / Northern NSW. It is created as pending; the operator confirms and the customer receives a payment link by email. No payment happens through this tool. Confirm all details with the customer first. Date/time use Queensland time (AEST, no daylight saving).

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": {
      "pickup": "<pickup>",
      "dropoff": "<dropoff>",
      "date": "<date>",
      "time": "<time>",
      "pax": "<pax>",
      "name": "<name>",
      "email": "<email>",
      "phone": "<phone>"
    },
    "name": "request_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
paxYesPassengers 1-16. Over 16 cannot be booked online - give the customer the phone number.
dateYesYYYY-MM-DD in Queensland time (AEST, no daylight saving) (at least 1 hour ahead; same-day: phone instead)
nameYesCustomer full name
timeYesHH:MM 24h in Queensland time (AEST, no daylight saving)
emailYesCustomer email (receives acknowledgement + payment link)
notesNoAnything else, e.g. child seats with ages (optional)
phoneYesCustomer phone
flightNoFlight number (optional, enables free flight tracking)
pickupYesPick-up place
dropoffYesDrop-off place
sandboxNoNot supported: true is refused (this endpoint has no test mode; a request creates a real booking). Omit it.
vehicleNosedan | carnival | maxi | eqb (Mercedes EQB luxury SUV, up to 3) | v300 (Mercedes V300 luxury van, up to 6) - auto-upgraded if too small for pax

Output Schema

NameRequiredDescriptionDefault
okNo
codeNo
errorNo
errorsNo
lodgedNo
statusNo
messageNo
requestNo
sandboxNo
vehicleNo
duplicateNo
price_audNo
referenceNo
amount_audNo
payment_urlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / date / description
      Previous value: -"YYYY-MM-DD (at least 1 hour ahead; same-day: phone instead)"New value: +"YYYY-MM-DD in Queensland time (AEST, no daylight saving) (at least 1 hour ahead; same-day: phone instead)"
    • changedInput schema / properties / time / description
      Previous value: -"HH:MM 24h"New value: +"HH:MM 24h in Queensland time (AEST, no daylight saving)"
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "description": "Lodged: ok true with the booking reference, status awaiting_payment and the payment link the customer also receives by email (duplicate true = the same request was already lodged in the last 10 minutes; nothing new was created). Sandbox connections: status sandbox_not_lodged, lodged false.",
      +  "properties": {
      +    "amount_aud": {
      +      "type": "number"
      +    },
      +    "code": {
      +      "type": "string"
      +    },
      +    "duplicate": {
      +      "type": "boolean"
      +    },
      +    "error": {
      +      "type": "string"
      +    },
      +    "errors": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "lodged": {
      +      "type": "boolean"
      +    },
      +    "message": {
      +      "type": "string"
      +    },
      +    "ok": {
      +      "type": "boolean"
      +    },
      +    "payment_url": {
      +      "type": "string"
      +    },
      +    "price_aud": {
      +      "type": "number"
      +    },
      +    "reference": {
      +      "type": "string"
      +    },
      +    "request": {
      +      "properties": {
      +        "date": {
      +          "type": "string"
      +        },
      +        "dropoff": {
      +          "type": "string"
      +        },
      +        "pax": {
      +          "type": "integer"
      +        },
      +        "pickup": {
      +          "type": "string"
      +        },
      +        "time": {
      +          "type": "string"
      +        },
      +        "vehicle": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "sandbox": {
      +      "type": "boolean"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "vehicle": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  3. Changed3 schema fields changed
    • changedInput schema / properties / pax / description
      Previous value: -"Passengers 1-11"New value: +"Passengers 1-16. Over 16 cannot be booked online - give the customer the phone number."
    • changedInput schema / properties / sandbox / description
      Previous value: -"true = create a TEST booking that never reaches the operator and sends no emails. For integration testing only."New value: +"Not supported: true is refused (this endpoint has no test mode; a request creates a real booking). Omit it."
    • changedInput schema / properties / vehicle / description
      Previous value: -"sedan | carnival | maxi (auto-upgraded if too small for pax)"New value: +"sedan | carnival | maxi | eqb (Mercedes EQB luxury SUV, up to 3) | v300 (Mercedes V300 luxury van, up to 6) - auto-upgraded if too small for pax"
  4. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (which only declare write/idempotent/openWorld flags), the description discloses that the record is created as pending, that an operator must confirm, that the customer receives a payment link by email, and that no payment flows through the tool. Timezone semantics (AEST, no DST) are also restated as a hard behavioral constraint. This is exactly the context the 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 highest-value fact (it is a REQUEST, created pending) followed by the no-payment caveat and the timezone rule. Self-contained and free of filler, though the AEST/no-DST sentence duplicates the schema and the pending-state point is stated twice ('REQUEST' / 'created as pending').

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 12-parameter, non-idempotent write with a real-world side effect, the description covers what an agent most needs: pending status, operator confirmation, email payment link, and no charge. An output schema exists, so return-value detail is rightly omitted; the remaining gap is the absence of any sequencing guidance relative to the sibling tools.

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 the schema already documents every parameter, including pax limits, date lead-time, and vehicle options. The description's only parameter-adjacent content — Queensland time, no daylight saving — only repeats what the date and time schema fields already say, so it adds no meaning beyond structured data.

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 description gives a specific verb and resource ('Lodge a booking REQUEST') and immediately bounds scope: private, fixed-price Queensland routes (Gold Coast/Brisbane airport, Cruise Terminal, Byron Bay/Northern NSW). The explicit '(not shared-shuttle)' carve-out lets an agent distinguish this from a generic shuttle booking without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is a workflow prerequisite ('Confirm all details with the customer first') and a clear exclusion (private, not shared shuttle), plus the note that no payment occurs here. However, it never routes the agent to the obvious siblings — check_availability or get_quote — or states whether availability/quotes must precede a request, which is the most likely mis-call for this tool.

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.