Last Minute Deals HQ

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

Annotations indicate this is a non-read-only, non-destructive tool, but the description adds valuable behavioral context beyond that. It explains that APPROVAL MODE creates a Stripe Checkout Session requiring immediate URL sharing, while AUTONOMOUS MODE completes bookings immediately with a confirmation number. It also notes bookings are 'real and go directly to the supplier,' clarifying the operational impact.

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 with the core purpose. Each sentence adds essential information: the two modes, their workflows, and when to use autonomous mode. There is no wasted text, and the information is presented in a logical, easy-to-follow manner.

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 complexity (two distinct modes, real-world booking impact) and lack of output schema, the description does a strong job of explaining the different outcomes (checkout_url vs. confirmation_number) and workflows. It could slightly improve by explicitly mentioning error cases or prerequisites, but it covers the key operational context well.

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 schema already documents all parameters thoroughly. The description adds some semantic context by explaining how wallet_id and execution_mode interact to enable autonomous mode, but it doesn't provide significant additional parameter details beyond what the schema offers.

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: 'Book a last-minute slot for a customer.' It specifies two distinct modes (APPROVAL and AUTONOMOUS) and differentiates from sibling tools like search_slots (which finds slots) and get_booking_status (which checks status). The verb 'book' is specific and actionable.

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 explicit guidance on when to use each mode: APPROVAL MODE (default) for standard bookings requiring customer payment, and AUTONOMOUS MODE when 'your application manages payment on behalf of the customer.' It also distinguishes from siblings by focusing on booking rather than searching or checking status.

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 provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, covering safety and idempotency. The description adds value by specifying the return data (status, confirmation number, service details, price charged), which isn't in annotations, but doesn't disclose additional behavioral traits like error conditions, rate limits, or authentication needs.

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 in the first sentence, followed by a concise list of return values. Every sentence adds necessary information without redundancy, making it efficient and well-structured for quick understanding.

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 low complexity (1 parameter, no output schema) and rich annotations covering key behavioral aspects, the description is mostly complete. It specifies the return data, which compensates for the lack of output schema, but could improve by mentioning error cases or when the tool might fail.

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%, with the booking_id parameter fully documented in the schema. The description adds minimal semantics by reinforcing the parameter's purpose ('by booking_id') and implying it's from book_slot, but doesn't provide extra details beyond what the schema already states, meeting the baseline for high 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 clearly states the specific action ('Check the status'), target resource ('a booking'), and key identifier ('by booking_id'). It distinguishes from siblings like book_slot (creation), get_supplier_info (supplier data), and search_slots (availability search) by focusing on status retrieval for existing bookings.

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 implicitly indicates usage when needing booking status details, with the required booking_id parameter suggesting it's for existing bookings. However, it lacks explicit guidance on when to use this versus alternatives (e.g., if status is already known from other operations) or any prerequisites beyond having a booking_id.

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 annotations already provide comprehensive behavioral hints (readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false). The description adds valuable context about what information is returned (destinations, experience categories, booking platforms, protocol details) and the tool's strategic purpose in the workflow, which goes beyond what annotations can convey. No contradiction with annotations exists.

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 perfectly concise with two sentences that each serve a distinct purpose: the first explains what the tool returns, and the second provides crucial usage guidance. There is zero wasted language, and the information is front-loaded effectively.

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 complexity (no parameters, comprehensive annotations, no output schema), the description provides excellent context about what information is returned and when to use it. The only minor gap is the lack of output format details, but the description compensates well by explaining the content categories that will be returned.

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?

With 0 parameters and 100% schema description coverage, the baseline would be 4. The description appropriately doesn't discuss parameters since none exist, but it does provide context about what information the tool returns, which helps the agent understand the output semantics despite the lack of an output 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 with specific verbs ('Returns information about the supplier network') and resources ('available destinations, experience categories, booking platforms, and protocol details'). It distinguishes from sibling tools by explaining this is for understanding available regions and activity types before using search_slots.

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 explicit guidance on when to use this tool ('Call this before search_slots to understand what regions and activity types are available'), creating a clear workflow relationship with a named alternative tool. This gives the agent clear context about the tool's role in the sequence of operations.

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 key behavioral traits (read-only, open-world, idempotent, non-destructive), but the description adds valuable context beyond this: it discloses the specific supplier sources (17 named providers), the sorting method ('sorted by urgency (soonest first)'), and the real-time nature ('real inventory'). No contradiction with annotations exists.

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 appropriately sized and front-loaded, starting with the core purpose. However, the lengthy list of 17 supplier names could be trimmed for brevity without losing essential context (e.g., summarizing as '17 Bokun suppliers'). The sentences are otherwise efficient and purposeful.

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 moderate complexity (search with filtering), rich annotations, and full schema coverage, the description is largely complete. It adds supplier details and sorting behavior not in structured fields. The absence of an output schema is a minor gap, but the description hints at return content ('Returns real inventory'), making it adequate for the context.

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?

With 100% schema description coverage, the input schema fully documents all four parameters (city, category, max_price, hours_ahead). The description adds minimal value by listing the parameters in a different phrasing ('Use city/category/hours_ahead/max_price to filter'), but doesn't provide additional semantic context beyond what's in the schema, meeting the baseline for high 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 clearly states the tool's purpose with specific verbs ('Search for last-minute available tours and activities') and resources ('real inventory from 17 Bokun suppliers'), distinguishing it from siblings like 'book_slot' (booking) and 'get_supplier_info' (supplier metadata). It explicitly mentions the OCTO open booking protocol, adding technical specificity.

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 explicit guidance on when to use this tool vs. alternatives: it instructs to 'Call get_supplier_info first to see all available destinations' for broader context, clearly differentiating from sibling tools. It also implies usage for last-minute availability searches, though it doesn't explicitly state when not to use it.

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