Search 650,000 hotels by place, vibe, photos and reviews. Search needs no key.
Scored across 3 tools
chat_about_hotels and search_hotels both retrieve hotels, but their descriptions clearly separate conversational/open-ended use from structured searches. get_hotel_details is fully distinct. Minor overlap remains, but an agent can reasonably select the right tool.
All names use snake_case and start with a verb (chat, get, search). chat_about_hotels inserts a preposition, which slightly breaks the clean verb_noun pattern, but the convention is otherwise predictable.
Three tools is within the typical well-scoped range. Each tool serves a clear, non-redundant function: conversational search, structured search, and detail retrieval. No tool feels extraneous.
The surface covers search, hotel details, and conversational exploration, which are the core read operations for a hotel search API. A booking or reservation tool is absent, but the server appears focused on information retrieval, so this is a minor gap.
Conversational hotel search for natural-language requests, comparisons and subjective preferences. Slower than search_hotels. Requires signing in (a linked Parley account) or an API key.
Guest context (travel style, purpose, accessibility needs, loyalty
programs, dietary needs) can be passed in the context parameter as a
JSON object.
Clarifications: if a previous response included a
``clarification_pending`` payload, show the question to the user and
either pass ``clarification_id`` + ``clarification_option_id`` for the
chosen option, or pass the user's free-text answer in ``message`` and
leave the clarification params empty.
Args:
message: The user's message or question
session_id: Session id from a previous response to continue the conversation (empty for a new session)
currency: Currency code for prices (default EUR)
context: JSON object with guest context (empty to skip). Example: {"travel_style": "luxury", "purpose": "honeymoon", "accessibility": "wheelchair", "loyalty_programs": ["Marriott Bonvoy"], "dietary": "vegetarian"}
clarification_id: When replying to a prior clarification, the id from ``clarification_pending.clarification_id`` in that response.
clarification_option_id: When replying to a prior clarification, the id of the option the user selected.
| Name | Required | Description | Default |
|---|---|---|---|
| context | No | ||
| message | Yes | ||
| currency | No | EUR | |
| session_id | No | ||
| clarification_id | No | ||
| clarification_option_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is covered. The description adds material behavior beyond the annotations: it requires authentication, is slower than search_hotels, is non-idempotent (session continuity changes results), and it documents the clarification flow. It doesn't cover rate limits or the shape of responses beyond clarification_pending, so it falls short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the purpose and the routing against search_hotels, then grouped into paragraph blocks for authentication, context, clarification handling, and args. It is appropriately sized for a 6-parameter conversational tool with zero schema coverage, though the clarification paragraph is slightly repetitive in wording.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given six parameters with no schema descriptions, no output schema, and a stateful multi-turn flow, the description supplies authentication requirements, session continuation, guest-context encoding, the full clarification protocol, and the comparison to the sibling tool. An agent has everything needed to invoke it correctly across turns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must carry the entire parameter burden, and it does. It explains message, session_id continuation semantics, currency with default, context as a JSON object with a concrete example, and exactly how clarification_id and clarification_option_id are sourced and used. No parameter is left ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb+resource (conversational hotel search) and explicitly separates it from the sibling search_hotels by listing the use cases it handles: natural-language requests, comparisons, and subjective preferences. An agent can tell it apart from get_hotel_details and search_hotels without opening the schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states when to use this tool (natural-language, comparative, or subjective hotel requests), names the alternative (search_hotels) and gives a selecting condition (slower), and includes prerequisites (sign in or API key). This is explicit when/when-not/alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full profile of one hotel by its hotel_id from search_hotels: description, amenities, images, rooms, guest reviews and guest insights. A price is included only when both check_in and check_out are given, as the all-inclusive total for that stay. Works without an API key (cached prices only).
| Name | Required | Description | Default |
|---|---|---|---|
| rooms | No | Number of rooms (0 = 1). Prices are only quoted for one room. | |
| guests | No | Number of adult guests (0 = default of 2). | |
| check_in | No | Check-in date, YYYY-MM-DD (today or later). Prices need check_in and check_out. | |
| currency | No | ISO 4217 currency code for prices, e.g. 'EUR', 'USD', 'GBP'. | EUR |
| hotel_id | Yes | The hotel's id (a UUID), as returned in hotel_id by search_hotels. | |
| check_out | No | Check-out date, YYYY-MM-DD, after check_in. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely useful non-schema context: pricing is an all-inclusive stay total, requires both dates, and works without an API key but only with cached prices.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core purpose, then the returned contents, then the pricing caveat. Content is tight with no filler, though the multi-line indentation and trailing whitespace make the raw text slightly awkward.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the burden of describing returns and does so by listing the profile sections. The pricing/auth caveat is included. Minor gap: no indication of response size, pagination, or image/media limits.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description reinforces the check_in/check_out coupling for pricing, but the schema already states 'Prices need check_in and check_out', so it adds little beyond the structured fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Full profile of one hotel by its hotel_id') and enumerates exactly what the profile contains (description, amenities, images, rooms, reviews, insights). It also anchors the tool against the sibling search_hotels by naming it as the source of hotel_id.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context: it must be called with a hotel_id obtained from search_hotels, and the description explains the conditional pricing behavior (price only when both check_in and check_out are supplied). It does not, however, explicitly say when to prefer chat_about_hotels or search_hotels instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the VistaLink hotel catalogue in one city (or around a point). Needs city, latitude+longitude, or hotel_name; describe the stay in vibe. Returns hotels with ratings, location, amenities, images and guest-review insights. A price appears only when both check_in and check_out are given (the all-inclusive total for that stay). Works without an API key (at most 20 results, cached prices only). For open-ended questions use chat_about_hotels.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City to search in, e.g. 'Lisbon'. A search needs city, latitude+longitude, or hotel_name. | |
| vibe | No | What the traveller is looking for, as free text or comma-separated tags, e.g. 'boutique design hotel' or 'romantic,quiet'. | |
| limit | No | Maximum number of results, 1-20 without an API key (1-50 with one). Larger values are reduced to the maximum. | |
| rooms | No | Number of rooms (0 = 1). Prices are only quoted for one room. | |
| guests | No | Number of adult guests (0 = default of 2). | |
| country | No | ISO 3166-1 alpha-2 country code of the city, e.g. 'PT'. Use it for city names that exist in several countries (Paris FR vs Paris US). | |
| check_in | No | Check-in date, YYYY-MM-DD (today or later). Prices need check_in and check_out. | |
| currency | No | ISO 4217 currency code for prices, e.g. 'EUR', 'USD', 'GBP'. | EUR |
| latitude | No | Search centre latitude in decimal degrees, used with longitude (0 = not set). | |
| amenities | No | Comma-separated amenities the hotel must have, e.g. 'wifi,pool'. | |
| check_out | No | Check-out date, YYYY-MM-DD, after check_in. | |
| longitude | No | Search centre longitude in decimal degrees, used with latitude (0 = not set). | |
| budget_max | No | Maximum price per night, in currency (0 = no maximum). | |
| budget_min | No | Minimum price per night, in currency (0 = no minimum). | |
| hotel_name | No | Hotel name or part of it, e.g. 'Four Seasons'. | |
| include_rates | No | Fetch live rates for check_in/check_out (adds about 30-45s). Needs an API key and both dates; ignored otherwise. | |
| radius_meters | No | Radius around latitude/longitude in metres (0 = default). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the no-API-key degradation mode (max 20 results, cached prices only), the rule that a price only appears with both dates, and that it is the all-inclusive total. It does not mention pagination or caching behavior of live rates beyond the 30-45s note in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core capability and preconditions, then constraints and the sibling routing. Dense but every sentence carries information; the parentheticals about pricing and the API key could be tightened slightly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 17-parameter search tool with no output schema, the description covers search modes, return contents (ratings, location, amenities, images, review insights), pricing conditions, and the free-tier limitation. What it lacks is guidance on how the many optional filters interact (e.g. budget vs. include_rates), but the essentials for correct invocation are present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter is already documented in the schema, making 3 the baseline. The description adds only the cross-parameter rule that prices require both check_in and check_out, which the schema also states per-field, so incremental value is limited.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Search the VistaLink hotel catalogue') plus its scope (one city or around a point). It also names the sibling to use for open-ended questions (chat_about_hotels), so the agent can distinguish it from siblings without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit preconditions ('Needs city, latitude+longitude, or hotel_name') and an explicit alternative for a different intent ('For open-ended questions use chat_about_hotels'). It also states the condition under which prices are returned, which governs how the agent should call it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
chat_about_hotelsget_hotel_detailssearch_hotelsSearch hotels & rentals: live prices & reviews across Booking.com, Airbnb, Vrbo & Google Hotels.
Search hotels, get live prices, and check out in chat. Guest search needs no sign-in.
Travel search: 1.3M hotels and apartments, owner homes, tours, flights, taxi, car rental.
Search and book 3M+ hotels in 200+ countries. Agents pay per reservation in USDC on Base over x402. Hosted, no auth.
Add one secure layer between your agents and this server.
