feat(tools): count and summarize every match in the area tools

aircraft_in_area and vessels_in_area return at most 200 rows, so a client
asked which operators dominate an area, or the average altitude there, could
only estimate from a truncated sample. Both tools now take an optional
group_by (aircraft: operator, origin_country, type_code; ships: type,
destination) and stats (airborne altitude and speed for aircraft, speed for
ships). Each is computed over every match before rows are capped. Breakdowns
list the ten largest groups plus other and unknown counts, and the summary
names the three largest.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

docs/CURRENT-STATE.md

@@ -93,7 +93,11 @@ perimeters, terrain height, military installations and map features, plus a
 combined situation brief, military awareness around a point, the app's heads-up display caption, and a link that
 opens the app over an area. Tools reuse the layers' portable source factories, take a
 shared `area` argument (place name, bounding box, or point and radius) and cap
-lists at 25 rows by default. Voice offers the same queries next to its app
+lists at 25 rows by default. `aircraft_in_area` and `vessels_in_area` can also
+count every match by a field (`group_by`: operator, country or type for
+aircraft; type or destination for ships; the ten largest groups, then other and
+unknown counts) and summarize airborne altitude and speed (`stats`: count, min,
+median, mean, max). Both cover all matches, not just the rows returned. Voice offers the same queries next to its app
 actions: the session lists them, and the browser runs them through the same
 catalog, loaded on first use. See [tools and the MCP server](TOOLS.md).