Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, yet it discloses only scope, not consequences. For an operation that removes data, it never says whether the action is reversible, whether clearing everything also wipes non-Canva state, or whether it disrupts an active session/auth. The prefix scoping is the only behavioral hint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.