Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered elsewhere. The description adds only the 'account-level' scope and says nothing about pagination, result size, or whether an empty result is possible for accounts without SD-WAN — for an open-world read that is the kind of context worth adding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.