Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes far beyond annotations by disclosing that the call clones structure, scoring/report configuration, visual settings, and all language versions in one call. It also surfaces the critical non-idempotency behavior: timeouts may have succeeded, so blind retries can create duplicates. This is exactly the kind of behavioral nuance an agent needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.