The room-level truth layer of hospitality. Verified scores for exact hotel rooms, not just hotels.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.3/5 across 8 of 8 tools scored.
Each tool targets a distinct aspect of hotel intelligence: search, details, pricing, rooms, nearby places, reviews, and room display. The only potential overlap is between get_hotel and ask_about_hotel, but the description clearly directs agents to use get_hotel first and ask only for supplementary questions.
All tool names follow a consistent verb-first snake_case pattern (e.g., get_hotel_pricing, search_hotels, show_rooms). The verbs vary (get, ask, search, show) but the pattern is uniform and readable, with no mixed conventions.
With 8 tools, the server is well-scoped for hotel intelligence. Each tool covers a necessary function without redundancy, staying comfortably within the ideal 3-15 range.
The tool surface covers the core hotel intelligence workflow: search, details, pricing, rooms, nearby, reviews, and presentation. The only notable gap is the absence of an actual booking or availability tool, but the server's purpose appears to be informational rather than transactional, so this is a minor omission.
add_special_requestAdd a special requestInspectAdd a special request to one of your bookings (e.g. extra pillows, late checkout, anniversary celebration). Requires connecting your Roomza account.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes | The special request to add | |
| booking_id | Yes | The booking ID to add the request to (get this from get_my_trips) |
| Name | Required | Description |
|---|---|---|
| ok | Yes | |
| message | Yes |
ask_about_hotelAsk about a hotelAAsk a specific question about a hotel that standard data may not answer. Uses AI with web search to find the answer. Examples: 'Does this hotel have Eiffel Tower views?', 'Is there a rooftop bar?', 'How far is it from the airport?'. Try get_hotel first; use this only when that data doesn't answer the question.
| Name | Required | Description | Default |
|---|---|---|---|
| hotel_id | Yes | Hotel UUID | |
| question | Yes | The specific question about the hotel |
| Name | Required | Description |
|---|---|---|
| answer | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=true, so the description doesn't need to cover safety. However, it adds important behavioral context by stating 'Uses AI with web search to find the answer,' revealing that results may come from external sources and are not limited to local data. This goes beyond the annotation's basic flag and sets appropriate expectations.
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?
The description is three sentences, each earning its place: purpose, examples, and usage guidance. It is front-loaded with the core function, then provides concrete examples and explicit alternatives. No redundancy or vague filler.
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 the tool's simplicity (2 params, no output schema, read-only, open-world), the description covers the key aspects: what it does, when to use it, and what kind of questions it can answer. It doesn't mention potential limitations like 'may return no answer' or 'may be slow,' but the openWorldHint and examples provide sufficient context for an AI agent to use it effectively. A small gap is the lack of explicit return format, but it's not critical for this question-answering tool.
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?
The input schema covers both parameters with concise descriptions (100% coverage), so the baseline is 3. The description adds value by providing example questions that illustrate the appropriate format and type of content for the 'question' parameter, going beyond the schema's generic description.
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?
Clearly states the tool's function: 'Ask a specific question about a hotel that standard data may not answer.' It uses a specific verb ('Ask') and resource ('hotel'), and explicitly differentiates from sibling tools by noting that it handles questions beyond standard data. The examples further clarify its purpose.
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?
Provides explicit usage direction: 'Try get_hotel first; use this only when that data doesn't answer the question.' This gives a clear when-to-use and when-not-to-use, naming the alternative tool, which is ideal for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_hotelGet hotel detailsAGet full details for a hotel including: Roomza Truth summary, score breakdown, top strengths, hotel character (type, vibes, best-for), nearby landmarks with distances, neighborhood, awards, amenities, and review highlights from the open web. Use hotel name, slug, or UUID as the identifier.
| Name | Required | Description | Default |
|---|---|---|---|
| identifier | Yes | Hotel name, slug, or UUID |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| hotel | Yes | null when the hotel was not found |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is known. The description adds context about the breadth of returned data, including 'review highlights from the open web,' but does not disclose behaviors like result size limits, error conditions, or whether the data is cached/aggregated. This is adequate but not rich.
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?
The description is notably detailed but efficiently front-loaded with 'Get full details for a hotel including:' followed by a compact enumeration. It is a single long sentence, but every listed item adds useful information about the tool's scope, with no filler or redundancy.
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 there is no output schema, the description does an excellent job of enumerating all the major categories of returned information. It also identifies the input requirement clearly. This is complete enough for an agent to understand what this tool provides and when it is the right choice.
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 coverage is 100% for the single parameter, and the schema already explains 'Hotel name, slug, or UUID.' The description repeats this exact guidance, adding no new meaning beyond what structured data provides, so the baseline score of 3 is appropriate.
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 uses a specific verb ('Get') and resource ('hotel details') and enumerates a clear set of data points (Roomza Truth summary, score breakdown, strengths, character, landmarks, neighborhood, awards, amenities, review highlights). This distinguishes it from sibling tools like get_hotel_pricing or get_hotel_rooms, which focus on narrower aspects.
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?
The description clearly conveys that this tool is for fetching full hotel details and specifies the accepted identifier formats. It does not explicitly mention when to prefer sibling alternatives, but the scope is clear enough that an agent can infer this is the comprehensive details endpoint.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_hotel_pricingGet room ratesAGet public room rates for a hotel (the hotel's own public rate; booking on Roomza never costs more). Pass check_in and check_out dates (YYYY-MM-DD) to get nightly from-prices per room type. Without dates, returns the hotel's typical nightly from-price. No booking links; to price and book an exact room, use secure_room.
| Name | Required | Description | Default |
|---|---|---|---|
| check_in | No | Check-in date in YYYY-MM-DD format (defaults to today) | |
| hotel_id | Yes | Hotel UUID | |
| check_out | No | Check-out date in YYYY-MM-DD format (defaults to tomorrow) |
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| found | Yes | false when the hotel is unknown |
| nights | Yes | |
| checkIn | Yes | |
| checkOut | Yes | |
| currency | Yes | |
| hotelName | Yes | |
| roomTypes | Yes | Per-room-type from-prices when dates were given and live rates exist |
| typicalNightlyFrom | Yes | Hotel-level typical nightly from-price in dollars |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds meaningful behavioral details beyond annotations: it returns public rates only, behaves differently with/without dates (nightly vs. typical rate), and explicitly notes no booking links. This adds context without contradicting the annotations.
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?
The description is three sentences, front-loaded with the core purpose, followed by usage conditions and a clear exclusion/alternative. Every sentence earns its place with no redundancy or filler.
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 simple read-only pricing tool with 3 parameters and no output schema, the description covers the essential invocation scenarios, default behavior, and what not to expect (booking links). It gives sufficient context for an agent to select and call the tool correctly, including naming the alternative for booking.
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 parameters are documented. The description enriches semantics by specifying the YYYY-MM-DD format for dates and explaining how the presence/absence of dates alters the output (nightly per-room-type prices vs. typical nightly from-price). This goes beyond the bare schema field descriptions.
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 uses a specific verb ('Get') and resource ('public room rates for a hotel'), clearly distinguishing it from booking-related tools like secure_room. It also implicitly differentiates from sibling tools like get_hotel_rooms by focusing on pricing rather than room details.
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?
Provides explicit context on when to use the tool: with or without dates, and states that booking links are not included. It names secure_room as the alternative for exact pricing and booking, giving the agent clear decision-making guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_hotel_roomsList hotel roomsAList rooms for a hotel with individual Roomza scores, bed type, view, and floor. Pass room_number to look up a specific room.
| Name | Required | Description | Default |
|---|---|---|---|
| hotel_id | Yes | Hotel UUID (get this from search_hotels or get_hotel) | |
| room_number | No | Look up a specific room by number, e.g. "434" |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| rooms | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds value by detailing the return fields (Roomza scores, bed type, view, floor) and the optional specific-room behavior. No contradictions with annotations.
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?
Two concise sentences, front-loaded with purpose and key details. No redundant or vague 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 a simple listing tool with two parameters and no output schema, the description adequately explains what is returned and the optional lookup behavior. It covers the essential information for an agent to invoke correctly.
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 description does not need to add parameter details. It reinforces the room_number usage but does not go beyond the schema descriptions.
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 clearly states the tool lists rooms for a hotel with specific details (Roomza scores, bed type, view, floor), using a specific verb 'List' and identifying the resource. It also notes the optional room_number lookup, which differentiates it from generic listing siblings like show_rooms.
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?
No guidance is provided on when to use this tool versus alternatives such as show_rooms or get_hotel_pricing. The description only explains the function and parameter usage, not tool selection criteria or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_my_preferencesYour preferencesGet your saved room preferences, standing requests, and loyalty accounts on Roomza. Requires connecting your Roomza account.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| preferences | Yes | |
| travelCards | Yes | |
| loyaltyPrograms | Yes | |
| standingRequests | Yes |
get_my_tripsYour tripsLook up your upcoming and past hotel bookings/trips on Roomza. Requires connecting your Roomza account.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| past | Yes | |
| count | Yes | |
| upcoming | Yes |
get_nearbyGet nearby places and eventsAGet nearby places (restaurants, bars, attractions, parks) and upcoming events near a hotel. Optionally filter events to a travel window with start_date / end_date.
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | No | Travel end date YYYY-MM-DD -- filters events to this window | |
| hotel_id | Yes | Hotel UUID (get this from search_hotels or get_hotel) | |
| start_date | No | Travel start date YYYY-MM-DD -- filters events to this window |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| events | Yes | |
| places | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint=true in annotations, the read-only behavior is already disclosed. The description adds the categories of places and event filtering, but does not reveal other behavioral aspects like output format, pagination, or time-related edge cases.
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?
Two sentences, front-loaded with the main purpose, then the optional filter. No wasted words or redundancy.
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 read-only tool with no output schema, the description covers what is returned (places and events) and the filtering option. It lacks details like distance radius or time horizon, but remains sufficient for the tool's simplicity.
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 coverage is 100%, providing baseline. The description adds meaning by explaining start_date/end_date as a 'travel window' for filtering events, and 'near a hotel' provides context for hotel_id. This goes beyond the schema's field descriptions.
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 clearly states the tool's function with a specific verb ('Get') and resource ('nearby places and events') near a hotel. It also lists example place types (restaurants, bars, attractions, parks), distinguishing it from sibling tools focused on hotel details, pricing, or search.
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?
The description implies usage context (near a hotel) and optional event filtering by travel window. However, it does not explicitly mention when to use this tool over siblings or when not to use it, so it falls short of the highest tier.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_recent_reviewsGet guest reviewsAGet verified guest reviews for a hotel, including comments and insider tips. Pass room_number to get reviews for a specific room.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of reviews (default 5) | |
| hotel_id | Yes | Hotel UUID | |
| room_number | No | Filter reviews to a specific room number, e.g. "434" |
| Name | Required | Description |
|---|---|---|
| note | Yes | Set when no reviews are returned, e.g. unknown room |
| count | Yes | |
| reviews | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is clear. The description adds context about content (comments, insider tips) and room filtering, but does not disclose ordering, pagination, default limits, or error behavior. Adequate but not deeply transparent.
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?
The description is two sentences with no redundant words. It front-loads the core purpose and then adds the room filter detail. Every word earns its place.
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 simple read-only tool with full schema coverage and a readOnlyHint annotation, the description provides enough to understand purpose and filtering. It lacks explicit mention of limit behavior or return format, but the schema covers the limit, and the tool is straightforward. Slightly above minimal.
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% for all three parameters, providing clear descriptions for limit, hotel_id, and room_number. The description's mention of room_number reinforces but doesn't add new semantic meaning beyond the schema. Baseline 3 is appropriate.
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 clearly states the tool retrieves 'verified guest reviews for a hotel, including comments and insider tips,' using a specific verb and resource. It distinguishes itself from sibling tools like pricing, rooms, and search by focusing on reviews, and the optional room filter adds precision.
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?
The implied use case is obvious: when you need guest reviews for a hotel. However, the description does not explicitly mention when not to use it or name alternatives, relying on sibling context. It provides a clear filter hint (room_number) but lacks explicit exclusionary guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_hotelsSearch hotelsASearch Roomza's hotel database by name, city, keyword, or natural language query. Understands hotel types (boutique, resort, luxury), vibes (romantic, trendy, quiet), traveler types (couples, families, solo), neighborhoods, and nearby landmarks. Example queries: 'boutique hotels in SoHo', 'romantic resort near the Eiffel Tower', 'pet-friendly hotel in Seattle'. Returns hotels with Roomza scores, tags, and landmark distances.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | Narrow results to a specific city | |
| limit | No | Max results (default 10) | |
| query | Yes | Hotel name, city, or keyword |
| Name | Required | Description |
|---|---|---|
| note | Yes | Search note, e.g. a nearby-city fallback explanation |
| count | Yes | Number of hotels returned |
| hotels | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: it understands hotel types, vibes, traveler types, neighborhoods, and landmarks, and returns hotels with scores, tags, and distances. This goes beyond annotations and helps the agent predict tool behavior, though it omits details like pagination or failure behavior.
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?
The description is well-structured and front-loaded: the first sentence states the core function, followed by capabilities and concrete examples. Every sentence adds useful information, and the examples are particularly valuable for an AI agent to understand query formats. No wasted words.
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?
The description is complete for a search tool with a simple schema: it explains return values (hotels with scores, tags, landmark distances), query capabilities, and example use cases. It does not explain limit/city handling or pagination, but those are covered by the schema and are not critical for a search operation. Given no output schema, the return description is sufficient.
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 coverage is 100%, but the description significantly enriches the 'query' parameter by explaining it supports natural language and specific dimensions (types, vibes, traveler types, landmarks). This goes beyond the schema's simple 'Hotel name, city, or keyword' and adds valuable guidance for formulating queries.
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 clearly states the tool searches Roomza's hotel database, with specific verbs and scope. It distinguishes from siblings by focusing on search across the database via name, city, keyword, or natural language, as opposed to getting specific hotel details or nearby places.
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?
The description provides clear context for when to use the tool: when searching hotels by various criteria, with examples showing natural language queries. It does not explicitly exclude alternatives or mention when to use get_hotel or get_nearby, but the examples and phrasing imply the appropriate use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
secure_roomPrice and lock a roomInspectPrice and lock an exact room for specific dates with Room Lock. Returns the live price, cancellation policy, and a secure booking link with the room preselected. Requires connecting your Roomza account.
| Name | Required | Description | Default |
|---|---|---|---|
| guests | No | Guest count (default 2) | |
| room_id | Yes | Room UUID (from show_rooms or get_hotel_rooms) | |
| check_in | Yes | Check-in date, YYYY-MM-DD | |
| check_out | Yes | Check-out date, YYYY-MM-DD |
| Name | Required | Description |
|---|---|---|
| ok | Yes | false = the request could not be quoted; see message |
| guests | Yes | |
| nights | Yes | |
| roomId | Yes | |
| checkIn | Yes | |
| hotelId | Yes | |
| message | Yes | Set when ok is false |
| bookable | Yes | true when a live bookable rate was found |
| checkOut | Yes | |
| currency | Yes | |
| rateName | Yes | |
| hotelName | Yes | |
| bookingUrl | Yes | Secure checkout link with the room preselected; payment happens only there |
| dueAtHotel | Yes | Additional amount due at the hotel, dollars |
| publicRate | Yes | Hotel's public rate in dollars, for comparison |
| roomNumber | Yes | |
| totalToday | Yes | Total charged today in dollars |
| trackRecord | Yes | Hotel's room-request honor track record |
| cancellation | Yes | |
| indicativeOnly | Yes | true when the price is from public listings, not bookable |
show_roomsShow roomsAREQUIRED whenever you present rooms. Whenever you are about to mention, recommend, or describe one or more specific rooms to the user, you MUST call this tool with those room UUIDs INSTEAD of writing the rooms in text. This is mandatory even when there is only ONE matching room — show it as a single hero card, never describe a lone room in prose. Call this BEFORE writing any prose about the rooms; the cards must appear first, then a brief summary. Pass room UUIDs (from get_hotel_rooms or search results) in ranked order, best first, 1 to 8 rooms. ALWAYS pass check_in and check_out when you know the user's dates: card prices are then for those exact dates. Without dates, cards show a typical from-price that can differ a lot from any specific dates. Each card shows photo, Roomza score, view, bed, and price. NEVER ask the user whether they want to see cards or images — just call this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| check_in | No | Check-in date YYYY-MM-DD. Pass whenever the user's dates are known so card prices match those dates. | |
| room_ids | Yes | Room UUIDs to display, in ranked order (best first). 1-8 rooms. | |
| check_out | No | Check-out date YYYY-MM-DD. |
| Name | Required | Description |
|---|---|---|
| rooms | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true. The description adds valuable behavioral context: renders cards with photo, Roomza score, view, bed, price; single room shows as hero card; cards must appear first. No contradiction with annotations.
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?
The description is a dense block of imperative instructions with no filler. Each sentence contributes operational guidance (when, how, constraints, timing, prohibitions), and the core requirement is front-loaded with 'REQUIRED whenever you present rooms.'
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?
Despite having no output schema, the description covers all necessary context: trigger, source of parameters, count limits, ordering, UI content, timing, and user interaction rules. An agent has everything needed to invoke the tool correctly.
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 coverage is 100%, so baseline is 3. The description adds the source of UUIDs ('from get_hotel_rooms or search results') which is not in the schema, and reinforces the ordering requirement. This provides meaningful value beyond the schema.
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 clearly states the tool's purpose: presenting rooms as cards to the user. It distinguishes it from sibling tools like get_hotel_rooms by explicitly saying 'INSTEAD of writing the rooms in text' and emphasizing this is for display, not retrieval.
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?
Provides explicit, mandatory usage instructions: must call whenever presenting rooms, call before any prose, pass ranked UUIDs, 1-8 rooms, and never ask the user. It clearly implies when not to use (when not presenting rooms) and removes ambiguity about alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
