Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safe pure-function profile is covered. The description adds the bidirectional behavior but omits practically important traits: how direction is inferred, handling of invalid characters, and the separator convention used in output.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.