Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only say readOnly=false, destructive=false, openWorld=false. The description adds genuinely non-obvious behavior: normalization to lowercase, per-account uniqueness, idempotent collision handling (returns the existing client instead of failing), and the owner email-confirmation gate on first grant. That is exactly the extra context annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.