Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral detail beyond those hints: the CPI mode returns 'the adjusted value, total change and average annual rate', specifies the data source (ONS monthly CPI index), the base year (2015 = 100), the supported date range, and that amounts are in GBP. This gives the agent a clear picture of what the tool does and what it returns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.