Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. 'List all emails' suggests a read-only operation, but the description doesn't address important behavioral aspects like pagination behavior (implied by 'limit' and 'after' parameters), rate limits, authentication requirements, or what 'all emails' means in terms of scope (user-specific, workspace-wide, etc.).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.