Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, which align with 'look up'. The description adds the behavior of looking up by email or username but does not disclose return format, not-found handling, or whether the lookup is exact. With annotations covering safety, this is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.