docs: document include_articles option for news tools

README.md

@@ -29,10 +29,16 @@ Health:
 1) `get_latest_events(topic, limit)`
 - `topic` is a coarse category: `crypto | macro | regulation | ai | other`
 
+Optional boolean:
+- `include_articles` (default: `false`) — when `true`, includes `articles[].url` + minimal fields per returned cluster.
+
 2) `get_events_for_entity(entity, limit)`
 - substring, case-insensitive match over extracted `entities`
 - uses a shallow recent scan first, then falls back to a wider historical scan if needed
 
+Optional boolean:
+- `include_articles` (default: `false`) — when `true`, includes `articles[].url` + minimal fields per returned cluster.
+
 ### Entity aliasing
 
 The server keeps a conservative alias map in `config/entity_aliases.json` for obvious shorthands
@@ -42,6 +48,9 @@ to reduce false misses, not to rewrite every possible name variant.
 3) `get_event_summary(event_id)`
 - Groq-written compressed narrative for a given `cluster_id`
 
+Optional boolean:
+- `include_articles` (default: `false`) — when `true`, includes the underlying `articles` list (with `url`) from the stored cluster.
+
 4) `detect_emerging_topics(limit)`
 - derives “emerging” signals from recent cached clusters