A scanned PDF is a photograph of a document. It looks like text to you and is nothing but pixels to the computer, which is why searching it finds nothing, selecting it selects nothing, and copying it copies nothing. This puts real text behind the picture, so all three start working.
The important thing is what it does not do: it does not redraw your page. The image stays exactly as it was, and the recognised words sit invisibly behind it. That is why a document processed here looks identical afterwards, and why the failure mode is a wrong word in a search rather than a page that suddenly looks different.
Accuracy depends on what you give it. Clean printed text comes out close to perfect. A third-generation photocopy or handwritten notes will have mistakes, and we would rather you knew that up front — search for a name you are certain is in the document, and you will know within seconds how well it went.
Two things about honesty here. First, if the document already has real text, this tool declines. Running recognition over correct text replaces something certain with a guess, which makes the document worse, and no amount of it looking like progress changes that. Second, in a document that is partly typed and partly photocopied — a contract with a scanned signature page, say — only the scanned pages are read. The typed ones are already right.
Where it runs is your choice, and it is a real one. On your device nothing is sent anywhere, and it takes longer — roughly four seconds a page. On our server it is faster and noticeably better with difficult handwriting, and your file is sent to us to do it. That choice is on the button, every time, not buried in a policy.