Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds a useful enumeration of what comes back (profile, public lists, images, listing/list counts), but nothing about pagination, visibility rules, or what happens for an unknown slug. Adds some value beyond annotations, not rich context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.