Why does chunking strategy (how you split documents before embedding them) meaningfully affect RAG answer quality?

Chunks that are too large dilute the embedding's specificity (a paragraph about five different subtopics doesn't closely match any single specific query) while chunks that are too small lose surrounding context needed to make sense of the excerpt on its own. Getting chunk size and overlap right is often the highest-leverage tuning knob in a RAG pipeline, more so than which embedding model you pick.