Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by explicitly stating 'It never reserves, charges, creates an intention or modifies data' and by describing the conditional availability/checkout URL behavior. This goes beyond the annotations and clarifies what the tool does and does not do during execution.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.