Due to being able to capture neutral buildings in one turn, the first player easily has an advantage. If they rush for a building between their opponent, there's nothing their opponent can do to stop them from getting it. And once they get it, it'll be at 5 health and it'll be almost impossible to take it back. I think maps should be made with "barbarian" owners of the cities. They'd start out at low health so nearby structures would be easy to capture, farther structures would be harder due to city health regen, and the opponent would have an opportunity to respond.
This has always been an issue in turn based strategy games. A general good practice when designing maps is to give player 2 an extra swordsman, so she can capture villages more quickly in the early turns without causing a significant long-term power advantage.
