Indeed, I didn't mean to imply that all doctors possess that skill in great amounts (or that, in any case, circumstances allow for full utilisation of the skill even if they do) or that medical history taking is therefore always of the highest standard. Obviously some doctors will be better at it than others, or more at liberty to use this skill than others (as you say, I could imagine a GP who only has 10 minutes per patient won't be as keen to start with fully open questions as a junior doctor in a ward who can clerk patients somewhat more freely).

Note that this isn't too different from, say, how software engineers are expected to be good at, and make good use of unit tests. But most probably don't (either because they never really cared to fully develop that skill, or their organisations applied contrary pressures leading to tech debt). But it is a recognised skill.

My main point was that, it is, in theory, a skill that doctors are expected to train (or at least pick up on during their practice), and therefore the same prompting principles that seem to apply here in the context of LLMs also interestingly seem to apply to medicine and history taking when "prompting" and interacting with humans.