I suppose in our new world of LLMs, using as few tokens as possible means you can cram more in a small context window, which could be helpful in various ways.
(I mean, you could skip the whole hallucination thing and write an exact converter, but that'd be a lot of effort for code that'd probably get used about as much as M-expression to S-expression converters do in the lisp world?)
https://arxiv.org/pdf/1912.05234