Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds that a primary contact is created alongside the account and that membership enrollment can happen inline, but it says nothing about duplicate handling, required permissions, or error behavior for a non-idempotent write.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.