List this agent's past bookings at Aurinia XO (check-out before today), most recent first — cancelled ones included (see the status field). Paginated: pass limit (default 20, max 100) and offset to page through history.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No |
| Name | Required | Description | Default |
|---|---|---|---|
| bookings | No |
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.
Add one secure layer between your agents and this server.
Each tool targets a distinct action: book creates a hold, cancel cancels, get_availability checks bed availability, list_current_bookings shows active bookings, and list_past_bookings shows historical ones. There's no overlap in purpose; even the two list tools are clearly separated by time horizon.
Names are mostly verb_noun (get_availability, list_current_bookings, list_past_bookings) with simple verbs (book, cancel) that follow a predictable pattern. The convention is consistent and easily inferable, with no mixed styles or ambiguous verbs.
With 5 tools, the server is well-scoped for a hostel booking domain. Each tool covers a core operation (available, book, cancel, list current/past) without redundancy or bloat, fitting the typical 3–15 range perfectly.
The surface covers the main booking lifecycle: check availability, book, cancel, and list bookings. The only notable gap is the lack of an explicit booking modification tool (e.g., change dates), but this is a minor omission given that cancellation and rebooking are possible. Door code retrieval is handled via list_current_bookings, so no dead ends exist.
