Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as safe, read-only, idempotent, and non-destructive. The description adds the scope ('all tools', 'current user') but does not disclose other behavioral aspects such as what 'available' means, whether it includes MCP tools, or response format. Since annotations cover safety, this is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.