Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, so the safety profile is covered. The description adds real value beyond those: the operation is scoped to the current API key user's own private watchlist, and it must only run on an explicit user request. It stops short of stating reversibility or permission requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.