Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, confirming this is a non-destructive write. The description adds minimal behavioral context beyond restating the projectId parameter's purpose ('inside a project'). It does not disclose permissions, idempotency, or error behavior, so the added value over annotations is low.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.