Workers AI Prompting: `assistant` messages as an output hint?

### Existing documentation URL(s)

- https://developers.cloudflare.com/workers-ai/features/prompting/

### What changes are you suggesting?

I can't find any text generation models that document this use of the `assistant` role instead of the LLM's turn in a conversation:

> Typically, the role can be one of three options:
> ...
> - **assistant** - Assistant messages hint to the AI about the desired output format. Not all models support this role.

Assuming it is accurate, the hint feature should probably be described in some model's parameter documentation.

### Additional information

_No response_