Skip to main content
Glama

Reserve a ride and pay for it automatically

reserve_and_pay
Destructive

Reserve a Quo ride and complete payment immediately, using the guest's already-linked card, only works if get_payment_method shows a linked card whose remaining 24-hour cap covers this fare. The fare is computed server-side from real pricing, never trusted from the caller. If the fare exceeds what is left of the guest's rolling 24-hour cap, or no card is linked, this refuses and suggests reserve_ride instead (a human-confirmed request with no charge). If the ride is created but the charge fails, the ride is NOT lost, it stays reserved and unpaid, and the response explains next steps. Requires session_token from verify_code.

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": {
      "session_token": "<session_token>",
      "pickup": "<pickup>",
      "when": "<when>"
    },
    "name": "reserve_and_pay"
  }
}

Input Schema

NameRequiredDescriptionDefault
whenYesPickup date and time, ISO 8601 (e.g. 2026-12-04T14:30:00-05:00)
hoursNo
notesNo
stopsNoOrdered intermediate stops between pickup and dropoff within this one reservation. Up to 3. Each stop adds a flat surcharge, and the trip is routed through the stops; both are included in the charged amount.
pickupYesPickup address, airport, or hotel
dropoffNoDestination, omit for an hourly/as-directed booking
serviceNotransfer
vehicleNosedan
flightNumberNoFor an airport pickup, Quo tracks the flight and the captain waits if it's delayed
session_tokenYes
idempotency_keyNoOptional. A unique string for this request (e.g. a UUID). If the call is retried with the same key, the original answer is returned instead of reserving and charging a second ride.
specialRequestsNo
additionalRidersNoOther named riders on this same booking, for a group/split-fare trip, the verified phone above stays the sole booking owner and the only one charged. Purely for the driver's manifest and, if a phone is given, that rider's own SMS ride updates.

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 already declare destructiveHint=true and openWorldHint=true, so the mutation risk is known; the description goes substantially further by disclosing that the fare is computed server-side and never trusted from the caller, and by spelling out the partial-failure state ('the ride is NOT lost, it stays reserved and unpaid, and the response explains next steps'). That partial-success semantics is exactly the non-obvious behavior an agent cannot get from annotations.

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-loads the action and the hard precondition, then layers failure modes in descending likelihood. Four sentences, all load-bearing; the middle fare sentence is dense but not padded. Slightly long, but nothing is redundant.

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 destructive mutation with no output schema, it covers precondition, refusal path, and partial-failure recovery well. The notable gap is retry safety: an idempotency_key parameter exists and the annotations explicitly say idempotentHint=false, yet the description never warns that a naive retry after a timeout could double-charge — the single highest-stakes omission here.

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 coverage is 54%, and the description's only parameter-adjacent content is the server-side fare computation and the 24-hour cap, neither of which maps directly to a named parameter. It says nothing about stops surcharges, additionalRiders/booking ownership, idempotency_key, hours, service, or vehicle — the schema descriptions carry those, so baseline 3 is appropriate but no value is added.

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 compound verb and resource — 'Reserve a Quo ride and complete payment immediately' — and immediately scopes it to 'the guest's already-linked card'. This cleanly separates it from reserve_ride, which the description later identifies as the uncharged, human-confirmed alternative.

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 ('only works if get_payment_method shows a linked card whose remaining 24-hour cap covers this fare'), a named prerequisite ('Requires session_token from verify_code'), and an explicit routing rule to reserve_ride when the cap is exceeded or no card is linked. An agent can decide between the two siblings without opening either schema.

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