You'd need to play with the different ones.
I tried 'Voiceover' (General > Accessibility > VoiceOver) on an iPhone. The way it works is you tap on the screen and it reads the element you have tapped on, and any relevant html i.e. "link: home", or "image: image of butterfly in a garden", you then double tap to activate the element. it will then tell you what has happened.
It's very hard to explain! But different accessibility tools work in different ways. On teh iPhone there is VoiceOver, Zoom, Speech, and then a variety of options within Display Accommodations too. They will each read different things in different ways depending on the interaction.
It would be lovely if there was one standard tool, or they all worked in the same way!