Add use-case guidance for semantic-embeddings RAG strategy

Add a "Best for..." statement to the semantic-embeddings description,
matching the pattern used by chunked-embeddings and BM25, so readers
can compare strategies at a glance.

Fixes #24571

Author: lacatoire

content/manuals/ai/docker-agent/reference/config.md

@@ -367,7 +367,7 @@ synonyms, and paraphrasing.
 #### Semantic-embeddings
 
 LLM-enhanced semantic search. Uses a language model to generate rich semantic
-summaries of each chunk before embedding, capturing deeper meaning.
+summaries of each chunk before embedding, capturing deeper meaning. Best for complex documents where context and relationships between concepts matter.
 
 | Field                              | Type    | Default |
 | ---------------------------------- | ------- | ------- |