Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description correctly aligns with 'Read'. It adds valuable context not in annotations: the tool requires no editToken and is specifically for post-OAuth management of durable websites, which gives agents insight into auth and workflow context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.