Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the side-effect profile. The description adds useful behavioral detail beyond the schema: rules are grouped by user agent, presets map to ready-made rule sets, and an optional sitemap line can be included.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.