Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the safety profile is largely covered. The description adds genuinely useful behavior — the dry-run default — though it doesn't say what the dry run returns, whether names must be unique, or what auth scope is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.