Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds meaningful behavioral context (Sedona's dark sky corridor, specific forecast components) without contradicting annotations. No mention of side effects or auth, but annotations cover safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.