But also Gemini supports contrained generation which can't fail to match a schema, so why not use that instead of prompting?
Even asking for JSON (without constrained sampling) sometimes degrades output, but also even the name and order of keys can affect performance or even act as structured thinking.
At the end of the day current models have enough problems with generalization that they should establish a baseline and move from there.
In general you can break any model by using a sampler that chooses bad enough tokens sometimes. I don't think it's well studied how well different models respond to this.