Document the lighting vision review and add describe_image to the tools inventory

TODO.md

@@ -209,6 +209,14 @@ licence-free zone only.
       day/late captures. (Attenuation is now gated: `test_venue_lights_use_physical_falloff`
       asserts every `OmniLight3D`/`SpotLight3D` in all three venues uses `attenuation = 1.0`,
       so a constant-falloff light cannot return unnoticed.)
+      Vision review 2026-11-03 (`tools/describe_image.py` on the night + flashlight captures):
+      the flashlight (`light_energy 4.2`, `spot_angle 14°`) washes the facade flat when pointed
+      at the door from close range and backlights the nearest NPC into a silhouette (staged-shot
+      artifact, but worth a shorter/softer cone or lower energy for the `06-night-flashlight`
+      stage); the El Capitan Theatre red marquee reads as a flat saturated block and the event
+      banners read as flat emissive decals rather than glowing signs — both are Compatibility
+      renderer limits (no bloom) plus the marquee's near-pure-red body; street lamps pool weakly
+      on near-black ground. No code change yet; these are owner-scorecard inputs.
 - [ ] Set dressing: review entrance and sidewalk prop clusters (`set-dressing`) for occlusion,
       navigation obstacles and readable storytelling clusters.
 - [x] Camera height: already decided in the 0.9.0 pass — keep the 1.7 m gameplay camera; the

tools/README.md

@@ -19,6 +19,7 @@ All tracked source files are listed here; generated `__pycache__/` and
 | [`build_releases.sh`](build_releases.sh) | shell: release export/packaging |
 | [`check_docs.py`](check_docs.py) | Python: documentation gate |
 | [`check_screenshots.sh`](check_screenshots.sh) | shell: gallery capture/compare |
+| [`describe_image.py`](describe_image.py) | Python: free-form vision review of captures/refs |
 | [`export_venues.gd`](export_venues.gd) | GDScript: venue `.tres` export |
 | [`export_venues.gd.uid`](export_venues.gd.uid) | Godot UID sidecar |
 | [`generate_textures.py`](generate_textures.py) | Python: procedural/AI textures |