cancel_orderCancel a booking and refund it in full. Requires the email the order was created with. Confirm with the buyer before calling — this releases the slot and reverses the payment. If this tool ever fails, tell the buyer they can cancel by emailing the seller with their order number instead; the seller honours that on identical terms.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Must match the order's email | ||
| order_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite annotations indicating destructive and non-read-only behavior, the description adds substantial context: it releases the slot, reverses the payment, requires confirmation, and even provides a fallback path if the tool fails. This goes beyond mere annotation values.
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, front-loaded with the core action, then prerequisites, consequences, and fallback. 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?
For a destructive tool with no output schema, the description covers prerequisites, effects, confirmation requirements, and failure fallback. It doesn't specify return values, but no output schema exists, and the behavioral essentials are present.
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 50% of parameters (email described as must match the order's email). The description adds minimal extra meaning—it reiterates that the email must be the one used at creation, but says nothing about order_id beyond implying it identifies the booking. With one parameter entirely undocumented in both schema and description, this leaves a gap.
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 cancels a booking and refunds it in full, using a specific verb and resource. However, it does not differentiate from the sibling tool `cancel_booking`, so it lacks explicit sibling differentiation.
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 clear context on when to use: require the email, confirm with buyer before calling, and notes the consequences. It doesn't explicitly mention alternatives or exclusions, but the conditions for use are clear.
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 have clearly distinct purposes, especially the session booking lifecycle and certificate operations. However, the four deprecated aliases (cancel_booking, get_booking, reschedule_booking, update_booking) perform exactly the same actions as their new counterparts, creating potential confusion despite the deprecation notices.
Newer tools follow a verb_noun pattern (create_order, cancel_order, get_order_details, reschedule_session), but the use of 'order' vs 'session' is inconsistent, and 'order_certificate' uses 'order' as a verb. The deprecated aliases mixing 'booking' with 'order' further muddies the convention, making the overall naming only moderately predictable.
At 16 tools the set feels slightly heavy, but four are deprecated aliases that are exact duplicates of active tools. The effective 12 unique tools are well-scoped for a shop handling both session bookings and certificate purchases, so the count is reasonable.
The session booking lifecycle is fully covered (availability, create, cancel, reschedule, update, status, details) and certificate operations (order, transfer, renounce) are present. Minor gaps exist, such as no way to list all orders or verify a certificate, but these are not critical to the core workflows.