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

Annotations already declare the destructive, non-idempotent, open-world profile, so the bar is lower; the description still adds real context — that cancellation is a two-step flow that emails the customer, one email per action, and that a paid booking is refunded in full by default. It stops short of spelling out irreversibility or permission requirements, but the side effects are well disclosed.

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?

Dense and front-loaded — the core action and its two branches lead, with consequences trailing. The trailing '(approve_url)' is cryptic and slightly muddies the close, keeping it from a 5.

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, non-idempotent mutation with 8 params, the description covers the consequences an agent most needs (email side effect, refund policy, two-step flow), and an output schema exists so return values needn't be explained. Minor gaps remain around series scope and the confirm_token purpose.

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 63%, and the description compensates for the biggest gap by explaining that item_id accepts either a waitlist wl_ id or a class cl_ id and what each does. It also confirms the refund default, though it leaves series, message, plugin_id, and confirm_token unaddressed beyond 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?

States a specific verb and resource ('Cancels a booking or declines a request') and immediately qualifies the resource variants: a wl_ entry_id removes a waitlist person, a cl_ class_id cancels the class. That level of specificity lets an agent distinguish this from edit_booking or approve_booking without opening a 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?

The description gives conditional behavior tied to item_id prefixes, which implicitly tells the agent which mode applies, but it never names an alternative tool or states when to prefer approve_booking, refuse_order, or edit_booking instead. Usage is inferable rather than explicit.

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