Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavioral detail beyond annotations: 25 successful calls, shared quota, 30-day validity, IP independence, exclusions, no email sent, and token delivery via X-Trial-Token or MCP metadata. This is consistent with readOnlyHint=false and openWorldHint=true.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.