When the microservice craze took off a lot of people asked me for opinions on it, and said the same thing then I say now: it more or less boils down to Conway's law. If you have multiple teams that need to iterate and deploy independently the overhead may be worth it. But if you're just a small startup with a single unitary dev team, and that generally just deploys a new version of any changed services all as one lump, it's an insane amount of complexity and overhead.