release_bookingGives an unpaid hold's seats back immediately, instead of letting them sit reserved until the 15-minute expiry. Call this when the buyer changes their mind. Paid bookings cannot be released.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | Language for titles, labels and the returned URLs. Defaults to fr. | |
| booking_uuid | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructive and idempotent behavior. The description adds useful context on top: release happens immediately versus waiting for expiry, and paid bookings are protected. These details help the agent understand real-world consequences beyond the annotation flags.
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, each adding a necessary detail: what happens, when to use it, and what cannot be released. There is no filler or redundant restating of the tool name or schema.
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 the essential precondition (unpaid hold), the alternative avoided (15-minute expiry), and the key constraint (paid bookings excluded). An output schema exists, so return values need not be described. For a small-footprint mutation tool, nothing needed for correct invocation is 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?
Schema coverage is only 50% because booking_uuid lacks a description, but the parameter is self-describing as the booking identifier. The description enriches it by specifying this must be an unpaid hold and that paid ones cannot be released, which compensates partially for the undocumented booking_uuid.
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 a specific action (release seats on an unpaid hold), the resource (booking/hold), and distinguishes it from simply letting the hold expire. It also excludes paid bookings, making the tool's scope unambiguous even without opening the schema.
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 says to call this when the buyer changes their mind, and clarifies that it should only be used for unpaid holds. This gives clear when-to-use guidance and a hard exclusion for paid bookings, leaving no ambiguity about the intended trigger.
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.
Most tools target distinct steps in the booking lifecycle, but get_booking_status and wait_for_payment serve nearly the same purpose, and get_event/list_events/get_availability all surface availability. Descriptions are strong enough to prevent frequent misselection.
All tools use a consistent verb_noun snake_case pattern (get_*, hold_tickets, redeem_*, release_booking, set_contact, wait_for_payment). There are no style or naming convention breaks.
Twelve tools map cleanly to the ticket-buying workflow: discovery, venue info, availability, hold, contact, payment, redemption, release, status, and recovery. Each tool earns its place without redundant bulk.
The lifecycle is well covered: hold, contact, payment, redemption, release, and post-sale recovery are all present. The only notable gap is lack of any cancellation/refund path for paid bookings, though this may be intentional venue policy.