Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and openWorldHint=true, indicating a write operation with external side effects. The description only adds 'by email,' which is largely redundant with openWorldHint and doesn't disclose additional behavioral traits like invitation acceptance or pending status.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.