The specs will be refined over time and won't be so cumbersome.
There was some research at Harvard where a student demonstrated using a camera projected a screen from his head and his hands could be used to move content around the screen and do signals (in much the same way sign language has developed) to bring up things like camera and zoom.
What they finally realised was that even with the most powerful projector in the world you can't go up against sunlight and hence the technology was useless.
Google glasses seem like a gimmick at the moment and they are. As is Siri from Apple.
However, one future generation of the smart device involves being able to see things within your vision not limited by phone form factor and being able to speak to your phone sort of like what Siri does today albeit much more advanced.
In the future, combining all these devices will allow a smart device to be hands free, voice activated and vision not limited by current form factors. You won't be looking down on your phone when using your car as you can see everything as an overlay through your glasses. You'll be able to talk to them like Siri to activate voice calls.
The last generation of smart phones used styluses. The current ones have touch and Siri-like.
The future ones will change things further.
If there is anything to be learnt, its to keep applications written for mobile devices small - otherwise rewrites for the next generation will be an even bigger chore!