Compares hotels either by explicitly specified hotels or by automatically selecting hotels within a given geographic area. This tool supports two mutually exclusive comparison modes: Explicit hotel comparison – compare a specific list of hotels provided via the locations parameter. Area-based comparison – compare a representative set of hotels automatically selected from a specified hotelArea. You must choose exactly one mode when calling this tool. Useful for comparing the ratings of various hotels' subratings like location, cleanliness, service, value, etc. The response includes key comparison fields like name, rating, price, amenities, etc. IMPORTANT USAGE RULES: 1. If the user requests to "compare hotels" in a city, area, neighborhood, or near/around a landmark/attraction, and does NOT name specific hotels, you MUST call this tool using the `hotelArea` parameter. 2. You do NOT need to wait for the user to name specific hotels. When they ask to compare hotels in a location (e.g., "compare hotels in Boston", "compare hotels in Paris", "compare hotels near Times Square"), you should immediately call this tool with the `hotelArea` parameter set to that location. 3. The tool will automatically select a representative set of hotels from the specified area for comparison. 4. Only use the `locations` parameter when the user explicitly names 2 or more specific hotels to compare. Examples of when to use hotelArea: - "Compare hotels in Boston" - "Compare hotels in Paris for Saturday" - "Compare hotels near Tower Bridge, London" - "Compare hotels near the Eiffel Tower, Paris" - "Compare hotels around Times Square" - "Compare hotels in Back Bay, Boston" Examples of when to use locations (specific hotels named): - "Compare Hotel Continental and Grand Hotel in Paris" - "Compare these hotels: Marriott Boston, Hilton Boston, and Hyatt Boston"

Retrieves comprehensive information for a specific hotel, including optional amenities, photos, live pricing, and guest reviews, based on user locale and stay dates. Use this tool whenever a user asks about a specific hotel by name, including: - Informational queries: "Tell me about X Hotel", "What are the amenities at X Hotel" - Qualitative questions: "How is X Hotel?", "Is X Hotel good?", "What do people think about X Hotel?" - Evaluative questions: "Is X Hotel a good option?", "Is X Hotel worth staying at?", "Would you recommend X Hotel?" - Suitability questions: "Is X Hotel good for families?", "Is X Hotel good for couples?", "Is X Hotel good for business travel?" - Any question where the user references a specific hotel and seeks information, opinions, or recommendations about it. If you do not get pricing details in the first response, you can recall the api with the same parameters (including the echoed back values of userId, sessionId and pageViewId) and it will return any additional pricing details that have become available since the first call. If you want to wait for pricing details to be available, you can set the 'pricingMode' parameter to QUICK, and the api will poll until either pricing details are available, or the timeout for that mode is reached.

Search for hotels matching the given criteria, using either a named location or a TripAdvisor GeoID. If the user has not provided a location, you should ask them for a location. If the user is asking for hotels with a proximity term, like near/within/close to etc, you should only pass the location specified after the proximity term to the API. For example "near the Louvre Museum, Paris" should be passed as "Louvre Museum, Paris" to the API. Likewise if "within 1 mile of London Eye", location should be passed as "London Eye" to the API. Results are displayed directly in an interactive map widget within ChatGPT, which already visualizes all hotels returned by this tool. If 0 hotels are returned - reflect it in your response to the user. Do not ask the user whether they want to see hotels on a map — they are always shown on the map automatically. The map widget already includes hotel details, so do not list or reprint the same hotels as text below the widget. You can ask the user if they want to filter the results, but do not use star rating. Instead you should use the term bubble rating. If you do not get pricing details in the first response, you can recall the api with the same parameters (including the echoed back values of userId, sessionId and pageViewId) and it will return any additional pricing details that have become available since the first call. If you want to wait for pricing details to be available, you can set the 'pricingMode' parameter to QUICK, and the api will poll until either pricing details are available, or the timeout for that mode is reached. The sortBy parameter should be BEST_VALUE by default. It can be set to PRICE_LOW_TO_HIGH if the user is specifically asking for the cheapest hotels. Likewise it can be set to DISTANCE if the user is asking for the hotels closest to a specific location or it can be set to POPULARITY if the user is asking for the most popular hotels. Response requirement: After showing results, the assistant MUST end its message with: "Do you want to compare any of these hotels? If yes, tell me at least 2 hotel names." The assistant MUST NOT end the message without this question