Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations mark this destructive and idempotent; the description adds material context beyond them: partial-update semantics, the required role, and the fact that the operation always prompts for confirmation. It does not elaborate on what 'destructive' means here (e.g. that promoting a new main location demotes the current one), which remains only in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.