Cancel a meeting you booked earlier in this conversation. Requires the manageToken returned by book-meeting — the same token that powers the cancel link in the customer's confirmation email. Removes the Google Calendar event and notifies both sides.
| Name | Required | Description | Default |
|---|---|---|---|
| manageToken | Yes | manageToken from the book-meeting response |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It transparently discloses that the tool removes the Google Calendar event and notifies both sides — clear side effects. It also discloses the token requirement as a behavioral dependency. Slight gap: it doesn't state error behavior when the token is invalid/expired or whether cancellation is irreversible.
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, front-loaded sentences with zero wasted words. The first sentence immediately states the action and prerequisite, the second ties the token to a user-facing artifact, and the third states the side effects. Excellent information density.
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 single-parameter tool with 100% schema coverage and no output schema, the description covers the essential behavior: what it does, prerequisites, and side effects. It could add note about failure modes or the manageToken's status requirement, but for the tool's limited complexity this is reasonably complete.
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 100% and the manageToken parameter's schema already documents its meaning. The description adds useful context by explaining the token's origin (from book-meeting) and its role (powers the cancel link), but this primarily re-emphasizes what the schema states rather than adding entirely new semantics.
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 uses a specific verb+resource ('Cancel a meeting you booked'), clearly scoping the action to bookings made 'earlier in this conversation.' It identifies the key prerequisite (manageToken from book-meeting) and distinguishes the operation from the sibling reschedule-meeting by focusing specifically 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?
States explicit context: only meetings booked in this conversation can be cancelled, and explicitly requires the manageToken, tying it to the cancel link in the customer's confirmation email. Though it doesn't name alternatives like reschedule-meeting, the 'you booked earlier in this conversation' scoping gives clear when-to-use guidance and implies the token requirement is a hard precondition.
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 or resource: product discovery vs pricing vs orders vs meetings vs support. While get-company-info, get-site-info, and get-guide all provide reference material, their scopes are clearly separated (verified facts vs FAQ/how-it-works vs published articles). No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern in snake_case: book-, cancel-, reschedule-, get-, search-, list-, request-, track-, reorder-, create-. Even exceptions like my-orders and my-invoices fit a possessive pattern that is predictable. No mixed conventions or vague verbs.
24 tools is on the high end but appropriate for the breadth of this server's scope: product catalog, pricing, meetings, orders, invoices, support, guides, company info, and SEO. Each tool fills a specific niche, and none feel redundant. It is slightly heavy but not overwhelming for the domain.
The tool surface covers the core workflows well: product search/details/pricing, meeting booking/cancel/reschedule, order viewing/tracking/reordering, quotes, complaints, callbacks, invoices, guides, and company information. A minor gap is the absence of a direct 'place new order' tool, but request-quote and reorder handle the necessary paths, and other interactions (e.g., complains) have clear entry points.
