Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior, but 'Project home dashboard' says nothing about what the tool returns, side effects, data scope, or permissions. An agent cannot infer whether this is a read-only view, a navigational hub, or something else.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.