Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that it only returns the user's own webhooks and never reveals the signing secret, which is important behavioral context. With no annotations, this description provides useful safety and security details, though it doesn't explicitly state read-only behavior beyond 'show'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.