Watch a hotel's price after your user booked it, and email them when it drops enough to rebook.
Scored across 2 tools
submit_hotel_booking and check_hotel_booking have clearly distinct purposes: one enrolls a booking into monitoring, the other queries its confirmation status. There is no overlap or ambiguity between the two tools.
Both tools follow the same verb_noun pattern: submit_hotel_booking and check_hotel_booking. The naming is consistent, predictable, and clearly indicates the action being performed.
With only two tools, the server is minimal, but the stated purpose is extremely narrow: enroll an existing hotel booking for price monitoring and check its confirmation status. Both tools earn their place, though the set is slightly thin.
The server covers the core create-and-check workflow for monitoring enrollment, but lacks operations such as canceling monitoring or listing all monitored bookings. These are notable gaps for a monitoring service, though agents can still complete the primary use case.
Check one booking you submitted, using the read token returned at submission. Use it to find out whether the traveller has confirmed yet: confirmed is false until they click the emailed link, and while it is false nothing is being monitored. Check here before telling your user their booking is being tracked.
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | The read_token from submit_hotel_booking. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It explains the meaning of the 'confirmed' field, that it is false until the traveller clicks the emailed link, and that nothing is monitored while it is false. This is valuable context beyond a simple status-check description.
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 filler. It leads with the core operation, then adds the most important behavioral nuance and a practical check-before-claiming instruction. Every sentence 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 one-parameter tool with no output schema, the description is complete: it explains the purpose, the token source, the meaning of the key status field, and when to use the tool. No important calling context is missing.
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 schema covers 100% of the parameter with 'The read_token from submit_hotel_booking.' The description echoes this by saying 'using the read token returned at submission,' but adds no new formatting or validation details. Baseline 3 is appropriate given full schema coverage.
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 states a specific verb and resource: 'Check one booking you submitted', using the read token returned at submission. It clearly distinguishes this tool from the sibling submit_hotel_booking by focusing on post-submission status checking.
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 explicitly says when to use this tool: to find out whether the traveller has confirmed, and specifically to 'Check here before telling your user their booking is being tracked.' This gives an actionable condition and prevents premature monitoring claims.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enrol a hotel booking the traveller has ALREADY made into free price monitoring. Rate Ranger watches what the hotel charges for the same dates and emails them if it drops far enough to be worth rebooking.
IMPORTANT: this monitors nothing on its own. The traveller is emailed one confirmation link, and no price is checked until they click it. Tell your user to expect that email. Do not tell them the booking is being tracked until check_hotel_booking says it is. Unconfirmed bookings are deleted after 7 days.
Use this only for a booking that already exists. It does not search for or make reservations.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | Optional name for you, such as my-assistant/1.0. Logged for debugging only. | |
| Yes | The traveller's own email address. One per call. The confirmation and any later price alerts go here, so it must be an address they actually read. | ||
| bookings | Yes | One to ten bookings for that traveller. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it delivers: it discloses the confirmation-email workflow, that no price is monitored until the traveller clicks the link, that unconfirmed bookings are deleted after 7 days, and that the user should expect the email. This is rich behavioral context beyond 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?
The description is front-loaded with the core purpose and then adds only high-value caveats: the confirmation link, the check_hotel_booking verification step, the 7-day deletion policy, and the existing-booking-only constraint. Every sentence earns its place without 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?
The description covers the essential workflow, timing, and verification path, and the schema fully documents the parameters. It doesn't describe the immediate return value or failure modes, but for a no-output-schema tool it provides enough context for an agent to invoke it and set user expectations 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 baseline is 3. The schema already explains email delivery, country affecting rate source, and hotel-name matching; the tool description adds little parameter-level meaning beyond that. It therefore meets but does not exceed the baseline.
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 opens with a specific verb and resource: 'Enrol a hotel booking the traveller has ALREADY made into free price monitoring.' It clearly distinguishes this tool from the sibling check_hotel_booking by focusing on submission/enrolment rather than verification.
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 explicitly states when to use it: 'Use this only for a booking that already exists. It does not search for or make reservations.' It also tells the agent not to claim tracking is active until check_hotel_booking confirms it, which is precise, actionable guidance.
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.
check_hotel_bookingsubmit_hotel_bookingTracks Agoda hotel prices for your dates, keeps checking, and shows what changed — with evidence.
Hotel booking MCP server. Search, book, and manage reservations across 250K+ properties worldwide.
Travel & commerce intelligence for AI agents: search, book & price-track hotels, events, retail.
Book real hotel and resort stays from any AI agent: all-in pricing, hosted Stripe checkout, no key.
Add one secure layer between your agents and this server.
