Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the risk profile is covered structurally. The description adds the business purpose but not what 'destructive' means here — e.g. whether an existing registration link on the number is replaced, whether unlinking is required first, or what happens if the registration is unapproved.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.