screenshot

Added value: +"http://json-schema.org/draft-07/schema#"

Removed value: -false

Added value: +9007199254740991

Previous value: -"1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. A frame from the window's composition surface (WGC: mode='background' with fullContent on a visible, non-minimised window when it can be, or normal mode's rescue) starts at the window's visible frame, and its origin is that frame's corner; when the visible frame cannot be read, no origin is given — the text says so; use desktop_discover for coordinates. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale."New value: +"1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. A frame from the window's composition surface (WGC: mode='background' with fullContent on a window visible on the current desktop — not minimised or cloaked — when it can be, or normal mode's rescue) starts at the window's visible frame, and its origin is that frame's corner; when the visible frame cannot be read, no origin is given — the text says so; use desktop_discover for coordinates. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale."

Added value: +0

Added value: +9007199254740991

Added value: +0

Added value: +9007199254740991

Previous value: -"Capture mode.\n  'normal'     — default. Window-targeted captures (windowTitle / hwnd) use Win32 PrintWindow with automatic BitBlt fallback when PrintWindow returns no data or an all-black frame; the route used is reported in hints.captureSource. Fullscreen / displayId captures use BitBlt.\n  'background' — a capture of the window itself, not of the screen: its composition surface (WGC) when it can be for a visible, non-minimised window with fullContent, else Win32 PrintWindow. Requires windowTitle (or hwnd). Pair with fullContent for GPU-rendered apps."New value: +"Capture mode.\n  'normal'     — default. Window-targeted captures (windowTitle / hwnd) use Win32 PrintWindow; when it returns no data or an all-black frame, the window's composition surface (WGC) is tried next if the window is visible on the current desktop (not minimised or cloaked), and BitBlt last. The route used is reported in hints.captureSource ('printwindow' | 'wgc' | 'bitblt-fallback'). Fullscreen / displayId captures use BitBlt.\n  'background' — a capture of the window itself, not of the screen: its composition surface (WGC) when it can be for a window visible on the current desktop (not minimised or cloaked) with fullContent, else Win32 PrintWindow. Requires windowTitle (or hwnd). Pair with fullContent for GPU-rendered apps."

Removed value: -false

Added value: +0

Added value: +0

Previous value: -"1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale."New value: +"1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. A frame from the window's composition surface (WGC: mode='background' with fullContent on a visible, non-minimised window when it can be, or normal mode's rescue) starts at the window's visible frame, and its origin is that frame's corner; when the visible frame cannot be read, no origin is given — the text says so; use desktop_discover for coordinates. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale."

Previous value: -"Capture mode.\n  'normal'     — default. Window-targeted captures (windowTitle / hwnd) use Win32 PrintWindow with automatic BitBlt fallback when PrintWindow returns no data or an all-black frame; the route used is reported in hints.captureSource. Fullscreen / displayId captures use BitBlt.\n  'background' — explicit Win32 PrintWindow capture, retained for back-compat and explicit selection. Requires windowTitle (or hwnd). Pair with fullContent for GPU-rendered apps."New value: +"Capture mode.\n  'normal'     — default. Window-targeted captures (windowTitle / hwnd) use Win32 PrintWindow with automatic BitBlt fallback when PrintWindow returns no data or an all-black frame; the route used is reported in hints.captureSource. Fullscreen / displayId captures use BitBlt.\n  'background' — a capture of the window itself, not of the screen: its composition surface (WGC) when it can be for a visible, non-minimised window with fullContent, else Win32 PrintWindow. Requires windowTitle (or hwnd). Pair with fullContent for GPU-rendered apps."

Previous value: -"Must be true to receive image pixels when detail='image'. Without this flag, detail='image' is blocked and a guidance message is returned instead. Prefer detail='text' / diffMode=true / dotByDot=true first — only set confirmImage=true when visual inspection is genuinely required."New value: +"Embed inline image pixels in the response. detail='image' now returns a cheap by-ref resource_link WITHOUT this flag (it is no longer blocked); confirmImage=true ADDITIONALLY embeds the inline image for immediate vision. detail='som' likewise returns its elements[] + a by-ref resource_link by default; confirmImage=true ADDITIONALLY inlines the annotated SoM bitmap. Prefer detail='text' / diffMode=true / dotByDot=true first — set confirmImage=true only when inline visual inspection is genuinely required."

Previous value: -"Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. BLOCKED unless confirmImage=true is also passed.\n  'som'   — Set-of-Marks image + OCR elements (bypasses UIA entirely). BLOCKED unless confirmImage=true is also passed.\n  'ocr'   — Windows OCR words with screen-pixel clickAt coords (Phase 4: absorbs former screenshot_ocr). Use when UIA returns no actionable elements (WinUI3 custom-drawn UIs, game overlays, PDF viewers). Note: detail='text' auto-falls back to OCR via ocrFallback='auto'; choose detail='ocr' only when forcing OCR unconditionally."New value: +"Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. Returns a cheap by-ref resource_link by default (no inline base64); pass confirmImage=true to ALSO embed the inline image.\n  'som'   — Set-of-Marks elements + annotated image (bypasses UIA entirely). Returns the OCR elements[] plus a cheap by-ref resource_link by default (no inline base64); pass confirmImage=true to ALSO embed the annotated bitmap.\n  'ocr'   — Windows OCR words with screen-pixel clickAt coords (Phase 4: absorbs former screenshot_ocr). Use when UIA returns no actionable elements (WinUI3 custom-drawn UIs, game overlays, PDF viewers). Note: detail='text' auto-falls back to OCR via ocrFallback='auto'; choose detail='ocr' only when forcing OCR unconditionally."

Removed value: -"ja"

Previous value: -"BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Used when detail='text' (OCR fallback) or detail='ocr' (direct OCR)."New value: +"BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Auto-detects from system locale when omitted. Used when detail='text' (OCR fallback) or detail='ocr' (direct OCR)."

Added value: +{
+  "description": "Optional response-shape opt-in. `['envelope']` returns the self-documenting envelope (`_version` / `data` / `as_of` / `confidence`). `['raw']` forces raw shape (overrides DESKTOP_TOUCH_ENVELOPE=1 server default). Default behaviour is raw shape (compat with existing clients).",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "Direct window handle ID (takes precedence over windowTitle). Obtain from get_windows (hwnd field). String type to avoid 64-bit precision issues.",
+  "type": "string"
+}

Previous value: -"Capture only the window whose title contains this string. Prefer over full-screen when target window is known."New value: +"Capture only the window whose title contains this string. Use '@active' for the current foreground window. Prefer over full-screen when target window is known."

Removed value: -"http://json-schema.org/draft-07/schema#"

Added value: +false

Removed value: -{
-  "description": "Stub tool — arguments ignored."
-}

Added value: +{
+  "default": false,
+  "description": "Must be true to receive image pixels when detail='image'. Without this flag, detail='image' is blocked and a guidance message is returned instead. Prefer detail='text' / diffMode=true / dotByDot=true first — only set confirmImage=true when visual inspection is genuinely required.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. BLOCKED unless confirmImage=true is also passed.",
+  "enum": [
+    "meta",
+    "text",
+    "image"
+  ],
+  "type": "string"
+}

Added value: +{
+  "default": false,
+  "description": "Layer diff mode — compares each window against the buffered previous frame. First call = full I-frame (all windows). Subsequent calls = only changed windows (P-frame). Implicitly enables dotByDot. Best used with windowTitle=undefined to snapshot all windows.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Capture a specific monitor (0 = primary). Use get_screen_info to list displays.",
+  "minimum": 0,
+  "type": "integer"
+}

Added value: +{
+  "default": false,
+  "description": "1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Cap the longest edge (pixels) when dotByDot=true. Reduces payload while preserving coordinate math. Example: 1280 on a 1920×1080 screen → scale≈0.667. Response includes scale factor: screen_x = origin_x + image_x / scale. Recommended for Chrome: dotByDot=true, dotByDotMaxDimension=1280, grayscale=true.",
+  "type": "integer"
+}

Added value: +{
+  "default": false,
+  "description": "Convert to grayscale before encoding. Reduces file size ~50% for text-heavy content (e.g. AWS console, code editors). Avoid when color is meaningful (charts, status indicators).",
+  "type": "boolean"
+}

Added value: +{
+  "default": 768,
+  "description": "Max width or height in pixels (default 768). Use 1280 to read small text, code, or fine UI details. Ignored when dotByDot=true.",
+  "type": "integer"
+}

Added value: +{
+  "default": "auto",
+  "description": "OCR fallback behaviour when detail='text'. 'auto' (default): fire Windows OCR if UIA returns 0 actionable elements OR hints.uiaSparse=true (UIA returned <5 elements, typical for Chrome). 'always': always augment actionable[] with OCR words. 'never': disable OCR entirely.",
+  "enum": [
+    "auto",
+    "always",
+    "never"
+  ],
+  "type": "string"
+}

Added value: +{
+  "default": "ja",
+  "description": "BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Only used when detail='text'.",
+  "type": "string"
+}

Added value: +{
+  "description": "Capture only this sub-region. Without windowTitle: virtual screen coordinates. With windowTitle: window-local coordinates — useful to exclude browser chrome (tabs/address bar). Example: windowTitle='Chrome', region={x:0, y:120, width:1920, height:900} skips the 120px browser chrome.",
+  "type": "object"
+}

Added value: +{
+  "default": 60,
+  "description": "WebP quality when dotByDot=true or diffMode=true. 40=layout only, 60=general (default), 80=fine text.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

Added value: +{
+  "description": "Capture only the window whose title contains this string. Prefer over full-screen when target window is known.",
+  "type": "string"
+}