The Hill Kinabalu

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds meaningful context by stating 'This is a read-only availability snapshot and does not create or hold a booking', reinforcing no-side-effect behavior and adding the max stay limit of 30 nights. These are behavioral details not present in 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 long, front-loading the purpose, then usage and constraints, then behavior. Every sentence delivers unique information 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 tool with a high-coverage schema, annotations, and an output schema, the description is complete: it covers what the tool does, required inputs, constraints, and the return type. The output schema handles return details, so the description need not elaborate further.

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 covers all three parameters with descriptions and validation, but the description adds crucial relational constraints: check-out must be after check-in, maximum stay is 30 nights, and the values must come from the user. This goes beyond the schema's per-parameter format and provides essential guidance for correct invocation.

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 'check' and resource 'room availability' for 'The Hill Kinabalu', scoped to an exact stay and party size. This clearly differentiates it from sibling tools like generate_booking_link (creates a link), list_rooms (lists rooms without availability), and get_wedding_information.

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 explicitly instructs to collect check_in_date, check_out_date, and total_pax from the user and never invent missing values, establishing clear prerequisites. It also gives date format and order constraints. However, it does not explicitly name alternative tools or when-not-to-use conditions, so it stops short of full 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?

The description discloses critical behavior beyond annotations: it validates availability, derives values server-side, returns nothing on missing/invalid/unavailable inputs, and explicitly states 'This creates no booking and holds no inventory.' This aligns with readOnlyHint=true and adds failure-mode detail, exceeding the baseline set by 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 sentences pack essential information: the action, prerequisites, a prohibition on fabricating values, and failure behavior. No redundancy or fluff; every clause earns its place, and the main action is front-loaded.

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 presence of an output schema, full annotation coverage, and a detailed description covering prerequisites, server-side validation, failure conditions, and side-effect disclosure, the tool is fully specified. No critical context is missing for an agent to select and invoke it 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?

The input schema already provides 100% coverage with descriptions for all four parameters, so the description adds marginal semantic value. It does cross-reference room_slug to check_room_availability, but this is more of a usage guideline than a parameter semantic. 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 generates a 'verified The Hill Kinabalu checkout link', specifies the required inputs (room_slug, check_in_date, check_out_date, total_pax), and distinguishes itself from siblings by referencing check_room_availability as the source of room_slug. This makes it unambiguous and sibling-discriminating.

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?

Explicitly states usage prerequisites ('only after the guest has supplied...') and directs users to use the room_slug from check_room_availability. It also warns against inventing values, providing clear when-to-use and when-not-to-use guidance relative to the availability-check sibling.

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 declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context: the information is official public data, limited to 2026/2027, includes specific data scopes, and explicitly rules out availability checking and enquiry submission. No contradictions.

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 sentences, each earning its place: the first describes what it retrieves, the second specifies when to use it, and the third states its limitations. The description is information-dense but well-organized and free of fluff.

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 (no params) and the rich annotations/output schema, the description covers all necessary context: purpose, usage guidance, data scope, and exclusions. It fully differentiates from sibling tools and leaves no significant ambiguity.

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 has no parameters, and schema description coverage is 100%. The baseline for 0-parameter tools is 4. The description does not need to explain parameters, and it correctly avoids adding irrelevant parameter details.

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 The Hill Kinabalu's official public wedding venue and 2026/2027 package information, listing specific data types like capacity, pricing, inclusions, and payment structures. It distinguishes itself from sibling tools by focusing exclusively on wedding-related information.

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 provides explicit usage triggers ('Use this when someone asks about weddings...') and explicit exclusions ('does not check date availability or submit an enquiry'), effectively guiding the agent to alternatives like check_room_availability for availability and generate_booking_link for enquiries.

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 declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false. The description adds context beyond these by clarifying the catalogue is 'official current' and that rates are 'indicative' and that it does not check date-specific availability, which is a key limitation.

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 usage guidance. Every word contributes value; no redundancy. Perfectly sized for an agent to understand and act on quickly.

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 (no parameters, output schema present), the description fully covers the data content, the authoritative source, and the limitation regarding availability. It is complete for an agent to decide when and how to invoke it.

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?

There are zero parameters, so the schema provides no additional semantics. The description sufficiently explains what the tool returns. A baseline of 4 is appropriate since no parameter documentation is needed.

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: retrieving The Hill Kinabalu's official current room catalogue with a specific list of data (room types, rates, capacity, beds, amenities, unit counts, images, booking links). It also distinguishes itself from availability check by explicitly saying this catalogue does not check availability.

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 guidance on when to use this tool: 'Use this when someone asks which rooms The Hill Kinabalu offers or what its room rates are.' It also tells when not to use it (does not check availability), implicitly directing to sibling tools like check_room_availability.

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