Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure burden. 'List Docker images' implies a read-only operation and the 'optional all filter' hints at filtering behavior, but it adds no extra context beyond the schema (e.g., default behavior, permission requirements, or return format). It is not misleading but is minimally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.