Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the annotations (readOnlyHint, openWorldHint, idempotentHint) by disclosing the billing model (flat /query rate, rendering free), the payment requirement, the need to read images with vision capability, the caveat that glyphs are for comprehension not verbatim quotes, and the instruction to open URLs for exact text. This is rich behavioral context that annotations alone do not provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.