I have the same problem and have no idea how to fix it.
I understand the thought is to describe the rooms but I am making a game for my students and they are now in the room where they have to use the verb 'to have' in a correct manner. I thought of talking statues that went blind and are desperate to know what they look like or something like that. Anyway they have to answer with things like "you have got long hair" etc. If I describe the statues myself instead of putting in a photo it kind of beats the goal
Have you figured it out yet?