Casona Signature — Personalized Cartagena Experiences

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds important behavioral context: unknown prices are excluded and the result must not be claimed as a confirmed quote or reservation. It does not describe pagination, output shape, or failure behavior, but those gaps are less critical given the read-only annotation.

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 compact sentences with the core action and key constraints front-loaded. Every sentence carries useful information, including the currency, draft status, unknown-price handling, and output limitation.

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?

No output schema exists, and the description sufficiently indicates that the tool returns a draft subtotal in COP. Combined with annotations and the simple one-parameter input, the definition gives enough context to invoke correctly, though it could clarify the result contents more explicitly.

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 parameter meaning. It says the calculation uses service IDs and quantities, which maps to the items[].id and items[].quantity fields, but it does not explain that quantity is optional, any default quantity, the maximum of 30 items, or how unknown IDs are handled beyond excluding their prices.

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: calculate a non-binding draft subtotal in COP from service IDs and quantities. This clearly distinguishes it from the sibling search tools, which retrieve experiences or quotes rather than computing a subtotal.

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 establishes that this is a draft, non-binding calculation and should never be represented as a confirmed reservation or quote. It implies use in pre-booking estimation, but does not explicitly name alternatives such as search_experiences or search_live_room_quotes or state when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/safe behavior, so credit goes to the added context: results are draft-catalog price references rather than live availability, which materially affects how an agent presents the data. Still missing pagination behavior for limit/offset and any note on ordering or result volume.

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, no filler, filter dimensions front-loaded before the price-reliability caveat. Every clause carries 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?

No output schema and low parameter coverage, but the description establishes source catalog, filterable facets, and the crucial limitation on what the returned prices mean — enough to call it responsibly. Residual gaps are the unexplained 'query'/'offset'/'limit' semantics.

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 only 17%, so the description must compensate. It explains category and menu examples but omits 'celebrations' from the category list, and lists venue as 'Costa/Vuelo' while the enum also allows Spa, Hotel and Extras — a misleading partial enumeration. The 'query' parameter is never explained.

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?

Specific verb+resource: 'Search the full Casona Signature v18 draft service catalog' with listed filter dimensions. It does not name sibling tools, but the note that results are 'COP price references, not live availability' implicitly separates it from search_live_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 'not live availability' caveat hints that live pricing requires a different tool, but the alternative (search_live_room_quotes) and the quoting path (draft_experience_quote) are never named. No explicit when-not or prerequisite guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly, openWorld, and non-destructive behavior. The description adds useful detail: live external source, COP full-stay totals, room and rate names, date-prefilled booking links, and an explicit no-booking-confirmation guardrail. It omits auth, rate-limit, and freshness caveats, keeping it from 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?

Three short sentences, front-loaded with the core action and followed by output details and the booking boundary. No filler or repetition.

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 read-only annotations and no output schema, the description explains return content and the booking boundary well. The remaining gap is parameter-level clarity for the hotel selection and guest breakdown, but overall it is sufficient for an agent to call the 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?

Schema description coverage is only 33%, with just checkIn and checkOut documented. The description says 'dates and guest counts' but does not explain the hotel enum values (both/COL/POR) or the adults/children/infants split and constraints, so it only minimally compensates for low 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?

States a specific read action against live SiteMinder room rates and availability through Casona Direct Booking, scoped by dates and guest counts. It is clearly distinct from the experience-focused sibling tools and makes the 'never confirms a booking' boundary explicit.

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 clear context: use it to read live room rates for given dates and guest counts, and it will not confirm a booking. It does not explicitly name alternatives, but the sibling tools are experience-focused, so the omission is minor.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.