Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds the scope 'in the document', which clarifies that block definitions across the entire document are included, but it does not disclose potential limitations like whether nested block definitions are included or the exact return format. Since annotations cover the safety profile, the description adds limited but useful context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.