How does it break down? Is it because the LLM didn't follow what you wrote down?
One, admittedly silly, example is Claude trying to put a light/dark theme switcher when you are trying to refactor the style of your small webapp.
I'm not against a theme switcher, but it is certainly not a trivial feature to implement. But Claude doesn't seem to understand that. And by having simpler prompts I feel it gets easier to steer the LLM in the right direction.