Aurinia XO

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

Discloses that the tool does not finalize the booking (returns a hold), that consent is one-time (~90 days), and that the stay is confirmed only upon payment. Adds context beyond annotations such as the pending_consent flow and payment_url 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?

The description is relatively long but front-loaded with the main purpose and then provides essential workflow details. Every sentence contributes to correct invocation, so the length is justified given the complexity of the consent and payment flow.

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?

Despite no output schema, the description explains the response structure (pending_consent vs hold with payment_url) and the required actions. It covers the entire booking workflow, including consent, payment, and eventual door code delivery via Telegram and list_current_bookings.

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 75% (3 of 4 parameters described). The description adds meaning by explaining that promo_code is optional and gives an example (BOT5), and clarifies that dates are for a range. The extra context about consent and identity not being needed adds value over the 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 'Book beds for a date range at Aurinia XO', specifying the resource (beds) and action (book). It distinguishes from siblings like cancel, get_availability, and list_bookings by focusing on the booking creation process.

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 instructs to not ask for confirmation before calling, to never hand the guest a self-service link, and details when to present a consent link (only if response has pending_consent). Also advises against asking for guest name/contact and explains the retry flow after consent.

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?

Adds detail beyond annotations: immediate action, no confirmation step, return format (booking_id, status, refund), error handling with reason, and consent policy. This fully informs agent behavior.

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?

Four focused sentences, each adding unique value: purpose, usage rule, return value/error, and consent. Front-loaded with core action. No wasted words.

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?

Covers cancellation flow, how to get booking_id, expected output, and consent. With output schema existing and sibling tools providing context, only minor details like reversibility are 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 only parameter booking_id is described as coming from list_current_bookings, which adds context to the 0% schema coverage. However, it does not define the parameter's meaning or format beyond that.

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?

Clearly states the action: cancel a hostel booking by its booking_id. Distinguishes from siblings like book (create) and list_current_bookings (list) by focusing on cancellation.

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 strong guidance: use booking_id from list_current_bookings, cancel decisively without re-asking, and consent is already handled. Lacks explicit comparison to alternatives like handling past bookings, but sufficient for most cases.

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 explicitly says 'Read-only' (consistent with the annotation), and adds context beyond annotations: the 'bed-places only' restriction and the effect of promo_code on price. It also mentions the default for check_out, though that is also in the schema. Since annotations already cover read-only, the description adds useful scope and pricing behavior.

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 purpose, then essential usage details. No filler words; every clause earns its place. The description efficiently conveys scope, read-only nature, default behavior, and promo code usage.

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 that an output schema exists (so return values need not be described) and annotations carry the safety profile, the description covers all necessary invocation details: purpose, location, scope, default behavior, and promo code. An agent can call this tool correctly without additional information.

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 75% (check_in, check_out, promo_code have descriptions; guests lacks one). The description repeats check_out default and promo_code example already present in the schema, so it adds little new meaning. It does not clarify guests or any additional parameter semantics, but the schema covers most parameters adequately.

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 the specific action ('Check dorm bed-place availability and price'), the resource ('Aurinia XO (Kamianets-Podilskyi)'), and the scope ('bed-places only, no room types'). This clearly distinguishes it from sibling tools like book, cancel, and list bookings, which are mutations or retrievals of different data.

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 implies when to use it: before booking, to check availability and price. It also notes 'bed-places only' which excludes room-type queries. However, it doesn't explicitly name alternatives or state when not to use this tool; the read-only annotation helps but the description doesn't discuss exclusion criteria beyond scope.

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 indicate readOnlyHint=true and openWorldHint=true. The description adds value by noting that cancelled bookings are included and explaining the door_code field lifecycle (null until issued, filled after payment). This provides behavioral context beyond the 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 concise sentences, each adding unique value. Front-loaded with the primary purpose, then nuance, then actionable guidance. No redundant or vague phrasing.

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?

Despite no parameters, the description covers use case, sorting, inclusion of cancelled bookings, and door_code behavior. With an output schema present, the agent has sufficient context for correct usage.

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 baseline is 4 per guidelines. The description does not need to add parameter semantics, but it contributes output field semantics (door_code behavior), which is appropriate given no parameters.

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 'list this agent's active/upcoming bookings' with specific criteria (check-out today or later, nearest arrival first). It distinguishes from sibling tools like list_past_bookings via the 'active/upcoming' qualifier.

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: 'Use this tool to give the guest their door code when they ask'. It does not explicitly contrast with siblings, but the context implies alternatives like book, cancel, get_availability, and list_past_bookings serve different purposes.

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 mark it as read-only and open-world. The description adds valuable behavioral details: cancellation inclusion, status field hint, and pagination behavior (default limit, max, offset). No contradiction with 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?

Three concise sentences front-load the main purpose, then add specific details. Every sentence earns its place with zero redundancy or 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?

The description covers key aspects: scope, sorting, cancellation, pagination. With an output schema present, the description is sufficiently complete for an agent to effectively use this 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?

Despite 0% schema description coverage, the description fully explains both parameters (limit and offset) with defaults and max/min values, adding meaning well beyond the bare 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 specifies the verb 'List', the resource 'past bookings' with a precise definition (check-out before today), and distinguishes from sibling tools like 'list_current_bookings' by focusing on past rather than current.

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?

While the name and scope imply when to use it (for past bookings), the description does not explicitly state when to prefer this over alternatives like 'list_current_bookings' or provide exclusions.

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