Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, covering the basic safety profile. The description adds nothing beyond that — no word on whether creation is persistent, what happens on duplicate names, or auth requirements for the config payload.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.