Live room rates and direct booking links for two boutique hotels in Cartagena, Colombia.
Scored across 2 tools
The two tools are cleanly split by intent: one is a static catalog of properties and booking-engine URLs, the other queries live SiteMinder availability and rates. The descriptions explicitly state that neither creates a booking, so there is no confusion about overlap with reservation behavior.
Both tools follow a strict verb_noun pattern (list_/search_) with a consistent domain prefix (casona). The nouns accurately reflect the returned resource (properties vs. room_quotes), giving predictable symmetry.
Two tools is thin for a rates-oriented server; the surface would benefit from at least a per-property detail or rate-policy lookup rather than forcing agents to rely on the quote payload. It is still a coherent, focused set with no redundancy.
The discovery-to-quote lifecycle for direct booking is covered and ends deliberately at a date-prefilled deep link, which is a reasonable dead-end-free design for an affiliate/rates server. Minor gaps remain (no single-property detail call, no explicit rate-policy or cancellation lookup), but agents can work around them from the quote output.
List the two Casona boutique hotels in Cartagena and their official direct-booking engine URLs. No availability is checked and no reservation is made.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the bar is lower; the description still adds useful context by stating what the result contains and explicitly ruling out availability checks and reservation creation. The fixed, tiny result set is hinted at by 'the two', though no pagination/rate-limit notes are needed here.
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 short sentences, front-loaded with the resource and scope, followed by the constraint. No filler or restatement of the title beyond what's needed.
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 parameters, no output schema, and full annotation coverage, the description supplies the essential missing piece: what the returned items are (hotels plus direct-booking URLs). An agent has everything needed to call it and interpret results, though it doesn't say the list is fixed at two entries beyond the phrase 'the two'.
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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The description correctly does not invent arguments.
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 (list the two Casona boutique hotels in Cartagena) plus what each record carries (official direct-booking engine URLs). The scope is narrow and unambiguous, and the mention of booking URLs clearly separates it from the sibling that searches room quotes.
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 negative clauses 'No availability is checked and no reservation is made' implicitly route the agent to search_casona_room_quotes for availability/pricing, and signal this is the discovery step. It stops short of naming that sibling explicitly, so the alternative is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check live SiteMinder room availability and indicative full-stay totals in COP for either or both Casona hotels. Returns room/rate names and date-prefilled direct-booking links. No booking is created; guest must confirm rates and terms in the hotel booking engine.
| Name | Required | Description | Default |
|---|---|---|---|
| hotel | No | Hotel: either Casona, or both (default). | |
| adults | No | Number of adults, default 2. | |
| checkIn | Yes | Guest arrival date YYYY-MM-DD, Cartagena local time. | |
| infants | No | Number of infants, default 0. | |
| checkOut | Yes | Guest departure date YYYY-MM-DD; 1–31 nights. | |
| children | No | Number of children, default 0. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description adds real domain context: data comes live from SiteMinder, prices are indicative full-stay totals in COP, and nothing is reserved. It stops short of saying anything about rate staleness, failures, or multi-currency handling.
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?
Three tight sentences, front-loaded with what it does, followed by what it returns and the non-booking caveat. Every sentence carries new information.
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 correctly describes the return payload (room/rate names, prefilled booking links) and the currency basis of the totals. Minor gaps remain around empty results or invalid date handling, but nothing essential to invocation 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?
Schema description coverage is 100% and every parameter (including the hotel enum and date patterns) is documented in-schema, so baseline is 3. The description adds only currency/scope framing, not parameter-level meaning beyond what the schema provides.
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 ('Check live SiteMinder room availability', 'full-stay totals in COP') and scopes it to the two Casona hotels. It is clear enough to distinguish from list_casona_properties by subject matter, though it never explicitly references that sibling.
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 the operative context (pre-booking rate research across one or both hotels) and the follow-up workflow ('No booking is created; guest must confirm rates and terms in the hotel booking engine'). It gives context but no explicit when-not-to-use or named alternative.
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.
list_casona_propertiessearch_casona_room_quotesLive hotel and resort prices (taxes included) and secure booking links for travelers. Since 1993.
Search hotels worldwide, compare live room rates, and create booking payment links.
Hotels that book direct: search, live-availability links, and AI-agent readiness checks.
Search, quote and book independent hotels: official rates, live availability, pay at the hotel.
Add one secure layer between your agents and this server.