Absolutely you lose a lot of effectiveness when you automate card creation. But it's still better than thinking, "Oh, I should make a card about this so I don't forget this important thing..." and never doing it.
For me the biggest risk is being tempted to making way too many cards (because it's so fast and easy now!), end up with way too many reviews, and declaring Anki bankruptcy and uninstalling the app after a few months. I may done this more than once...
imo if you don't make the card then either: the word isn't important, or it comes up again, and you finally do make the card. It's not a big deal.
I'm about 10 years on my Anki deck and have reached the same conclusion as you about keeping deck size down. A single card has a huge time investment if you add up the reviews. Even more if it's a bad card and you fail it a lot. As the words you learn get more and more niche, it's important to weigh up whether a card is worth making or keeping. I actively delete cards that make me feel 'meh' when I see them, or that I fail a lot, so I don't lose motivation.
These days I have a policy to just suspend once the interval hits six months, so that deck size has a max cap and can eventually go to zero if adds stop for a long enough period. Long enough to bootstrap niche words and hopefully maintain them through reading.
For me the biggest risk is being tempted to making way too many cards (because it's so fast and easy now!), end up with way too many reviews, and declaring Anki bankruptcy and uninstalling the app after a few months. I may done this more than once...