Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description merely repeats the action 'delete' without elaborating on consequences (e.g., cascading deletions, reversibility, or permission requirements). Annotations already indicate destructiveHint=true, but the description adds minimal value beyond that. It also incorrectly includes 'workspace_slug' in the args, which is not present in the input schema, creating confusion.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.