Likely because it's just easier to see if the LLM solution works. When it doesn't, then it makes more sense to move into deterministic workflows (which isn't all the hard to build to be honest with Claude Code).
It's the old principle of avoiding premature optimization.
A quick scan of the "partners" for A2A includes many of the same groups that helped launch AGNTCY. Either they jumped ship or they're teaming up with everyone. The Google announcement does read like marketing hype, though, so it remains to be seen how functional it is.
It's the old principle of avoiding premature optimization.