activity_availability
ChatGPTPriced tickets for one visit date. Returns compact offers[] with offerId. Required: activityCode, travelDate, and ageBands (or adults). Checkout uses correlationId + offers[].offerId.
activity_calendar
ChatGPTCompact availableDates[] for an activityCode. Pick one date as travelDate for activity_availability. Do not invent a visit date when the list is empty.
activity_details
ChatGPTCompact activity content, age bands, and booking questions. Pass activities[].activityCode and correlationId from search_activities. startDate may be omitted when this session already has one.
activity_get_checkout_url
ChatGPTCheckout one offers[] row. Pass correlationId + offerId from activity_availability. Activity, date, grade, start time, and party are filled from that session. Include bookingQuestionAnswers when activity_details listed required questions. Deeplink returns a portal url. ACP returns a secure payment page url. Show that link. This chat cannot charge the card. Explicit activityCode, travelDate, and gradeCode still work.
activity_locations
ChatGPTAutocomplete destinations. Returns compact locations[]. Pass locations[].destinationId as search_activities destination. Do not invent a destinationId.
car_get_checkout_url
ChatGPTCreate a secure checkout link for a selected rental car. Use after rate revalidation. The user completes payment and driver details on the RouteStack portal.
car_locations
ChatGPTLook up car pickup and drop-off locations by city or airport code. Use when the user names locations for a car search.
car_revalidate
ChatGPTConfirm the current price of a selected rental car offer before checkout.
car_search
ChatGPTSearch available rental cars for pickup and drop-off locations, dates, and times. Use after resolving location codes with car_locations.
flight_get_checkout_url
ChatGPTCreate a secure checkout link for a selected flight. Use after fare revalidation. The user completes payment and traveler details on the RouteStack portal.
flight_locations
ChatGPTLook up airports and cities by name or IATA code. Use when the user names origin or destination for a flight search.
flight_revalidate
ChatGPTConfirm the current price of a selected flight fare before checkout.
flight_search
ChatGPTSearch available flights for origin, destination, dates, and passenger count. Use after resolving airport codes with flight_locations.
flight_session
ChatGPTStart a flight search session. Use before flight_search when a session is required.
get_hotel_details
ChatGPTProperty details (compact). Prefer hotels[].hotelId from hotel_search; correlationId/token filled from the cached search session when available.
hotel_get_booking
ChatGPTRetrieve details for an existing hotel reservation by booking ID.
hotel_get_checkout_url
ChatGPTCreate a secure checkout link for a selected hotel room. Use after rate revalidation. The user completes payment and guest details on the RouteStack portal.
hotel_get_details
ChatGPTGet property details for a hotel including description, amenities, images, policies, and contact information.
hotel_get_rooms_and_rates
ChatGPTList available room types and rates for a selected hotel. Use after the user picks a hotel from search results.
hotel_revalidate_rate
ChatGPTConfirm the current price and availability of a selected room rate before checkout.
hotel_search
ChatGPTSearch available hotels for specific check-in and check-out dates. Use after resolving a destination ID. Returns listing results and session fields needed for follow-up calls.
hotel_search_destinations
ChatGPTLook up cities, neighborhoods, and hotel names. Use when the user names a place and you need a destination ID before searching hotels.
search_activities
ChatGPTSearch activities for a city name or a destinationId from activity_locations. Optional filtering/sorting/pagination map to CTS ActivitySearchV2. Prices are returned in the member currency. Returns compact activities[] plus correlationId and pagination (totalCount/hasMore). Next: activity_details, then activity_availability. Do not invent activityCode.
search_cars
ChatGPTSearch rental cars. Returns compact offers[] — each has fareCode and car (for checkout). Also echoes pickup/dropoff/pickupDate/dropoffDate/correlationId. Persist those; do not invent fareCode. Location and schedule fields (MCP normalizes aliases for all clients — AI Chat, ChatGPT, Claude, MCP connectors, etc.): Preferred shape: pickup/dropoff objects each with { name, code?, date, time }. Accepted flat aliases on the same tool call: pickupPlace, dropoffPlace, pickupDate, dropoffDate, pickupTime, dropoffTime (and snake_case pickup_location, pickup_date, pickup_time, pickup_location_code, etc.). Empty pickup/dropoff {} objects are ignored when flat aliases are present. Interpret the traveler's natural language into these structured fields — MCP does not parse raw chat. Airport codes (IATA): when the traveler gives a code such as SFO, LHR, or LAX, set pickup.name (and preferably pickup.code) to that code; MCP resolves it via CTS car locations autocomplete for every MCP client — do not invent internal location IDs. Use car_locations (car_search_locations) to resolve name/code when unsure — never put rental company names in pickup.name. Ambiguous cities/airports (works worldwide, not just London — MCP resolves this from live location data, not a hardcoded list): When the traveler names only a city/region that has multiple airports and does not name one specific airport (examples: "London Airport", "airport in London", "any airport near London", "flying into London", "car rental at a London airport", "New York Airport", "Paris Airport", "Tokyo Airport", "Dubai Airport", "Mumbai Airport", "Delhi Airport"), pass the traveler's place name plus "Airport" as pickup.name/dropoff.name exactly as given (e.g. name: "London Airport") — do NOT silently pick one specific airport (e.g. do not default to Heathrow/LHR or any other single airport) and do not invent a code. If car_search (or car_locations) responds with code "CAR_LOCATION_AMBIGUOUS", it means multiple airports matched — the response includes a candidates[] array of { name, code } for every matching airport. You MUST stop and ask the traveler to choose one from that exact list before calling car_search again; never auto-select a candidate, even if one seems "most likely" or most popular. Once the traveler names one airport (by name or code), call car_search again with that exact airport in pickup.name/pickup.code (and dropoff too, if it was also ambiguous). Every user-requested constraint must appear together in filters on the same car_search call. Each supported filter dimension is independent — any subset (2, 5, 9, or all filters) uses the same flow with logical AND. Do not drop, omit, or merge away a filter because others are present. Never split inventory filters across findData — prefer filters.* keys; MCP merges aliases and applies every dimension. You must infer the total traveler/seat count from natural language and emit structured numbers — MCP does not parse raw chat text. Count every person who needs a seat (adults, children, infants unless the user excludes infants). Examples (emit minPassengers; add maxPassengers equal to the same N when the user wants exactly N seats): "7 seater" / "7-seater" / "7 passenger" / "7 seats" / "7 people" / "car for 7 adults" / "we are 7" → minPassengers 7, maxPassengers 7; "5 passenger car" / "for 5 people" / "five seats" → minPassengers 5 (maxPassengers 5 if exact); "me and my friend" → 2; "me and my wife" → 2; "me and my wife with 3 kids" → 5; "family of 4" → 4; "travelling with 3 people" / "group of 6" / "5 friends" → minPassengers equals the counted total; "need a family car" without a number → infer a reasonable minimum from context (often 4–5) or ask one clarifying question before searching. For "at least N" or "N or more" set minPassengers only (omit maxPassengers). For exact N-seater requests ALWAYS set minPassengers and maxPassengers to the same N — never rely on carCapacity 6_or_more alone for a specific count. Use carCapacity buckets (2_to_5, 6_or_more) only when the user asks for a broad range with no exact number.
search_destinations
ChatGPTLook up cities/neighborhoods/hotels. For a named property (e.g. Avari Apartments), query the full hotel name and use the Hotel-type row. MCP remembers that row so hotel_search can apply hotel focus even if destinationType/hotel_name are omitted. Use destinationId, lat, and long from the chosen result row for hotel_search — never invent IDs.
search_flights
ChatGPTSearch flights. Returns compact offers[] — each has fareSourceCode and flight (for checkout). Also echoes origin/destination/departureDate/adults/children/infants/searchFilterObj/correlationId. Persist those; do not invent fareSourceCode.
search_hotels
ChatGPTCRITICAL for a named hotel: pass filters.hotel_name (e.g. "Avari Apartments") OR destinationType "Hotel" / isFromSingleHotel true. If you only pass destinationId from a Hotel destinations row, MCP still applies hotel focus from remembered metadata. City/area search → City destinationId, no hotel_name. Occupancy is required from the traveler (rooms[].adults); never invent 2 adults. Optional sortBy is one of { price: "ASC"|"DESC" }, { rating: "ASC"|"DESC" }, { saving: "ASC"|"DESC" } and is applied to the full listing. Returns compact hotels[] plus correlationId/token.
search_vr
ChatGPTSearch vacation rentals. Pass destination (e.g. Las Vegas) or a vr_locations row, plus checkIn and checkOut. A place name is resolved to the supplier city before search. Returns compact resorts[] plus correlationId. If the exact dates have no inventory, a nearby week or month that does is returned in checkIn/checkOut. Next: vr_details with resorts[].resortId, then vr_availability. Do not invent resortId.
vr_add_order
ChatGPTCreate a VR order (addOrder mutation). Pass the full AddOrder input from CTS.
vr_availability
ChatGPTPriced units for a resort. Returns compact offers[] with offerId. Required: resortId, checkInDate, checkOutDate, and correlationId from search_vr. Checkout uses correlationId + offers[].offerId.
vr_details
ChatGPTCompact property details. Pass resorts[].resortId and correlationId from search_vr. The full content is cached for checkout. additionalCharges are informational only — never add them into bookable Total; use vr_availability offers[].payable as Total.
vr_locations
ChatGPTAutocomplete VR destinations. Returns compact locations[]. Use city/state/country + type as location input to search_vr.