Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond that: the 1-based paging convention and, more usefully, that company results expose a slug that routes to the detail tool. No auth or rate-limit detail, but the added workflow insight is meaningful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.