Skip to main content
Glama

Paint a photo with Todrawn Scribe

scribe_paint_image
Read-onlyIdempotent

Paint a local PNG or JPEG as a Todrawn pen-stroke drawing: creates an underpaint, replays colored strokes as a video, and returns a shareable link while the image stays local.

Instructions

Paints a local photo or picture (PNG or JPEG) as a Todrawn Scribe drawing: an underpaint first, then thousands of coloured pen strokes, replayed by the pen as a video. The image is processed on this machine and never uploaded; the returned link carries only the strokes. Long paintings are capped at 180 s of playback. Previewing is free and needs no account. Exporting the MP4 needs a free Todrawn account: the Free plan allows 5 exports per UTC day and ends each video with a "Made with Todrawn Scribe" card; Premium has unlimited exports, makes the card optional and also exports 2160p (4K) and 60 fps.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "imagePath": "<imagePath>"
    },
    "name": "scribe_paint_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
penNoPen width shapes the painting: fineliner (default) is the finest, marker the boldest. Chalk draws a grainy chalk line and is meant for background: "dark".
aspectNoArtboard: landscape 16:9, portrait 9:16, square 1:1, feed 4:5. Defaults to the one closest to the image's shape.
detailNoStroke budget: low ~1200 strokes, medium ~2000 (default), high ~2800. More detail is more faithful and plays longer.
localeNoLanguage of the Scribe interface the link opens. Defaults to en.
densityNoSpacing of the board pattern's marks, 16 to 192, even numbers only (default 28). Larger is sparser.
patternNoMarks printed on the board behind the writing: dots, lines, grid, staff, vertical lines or blank.
imagePathYesPath to a local PNG or JPEG file. Relative paths resolve against the server's working directory.
backgroundNodark board or light paper.
cameraTiltNoCamera angle above the board in degrees: 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90. 40 is the standard view, lower is flatter and shows more depth, 90 looks straight down. Applies to the 3D pen view only (its preview and its export); the flat 2D view ignores it.
cameraZoomNoCamera framing of the 3D pen view (its preview and its export) in percent: 75, 100, 125, 150, 175, 200; 75 shows the most board, 200 follows the pen closest. The flat 2D view ignores it. Not the same as a passage's zoom.
cameraRotationNoCamera rotation around the board in degrees: -45, -40, -35, -30, -25, -20, -15, -10, -5, 0, 5, 10, 15, 20, 25, 30, 35, 40, 45. 0 looks straight on, negative moves the camera to the left of the board, positive to the right. Applies to the 3D pen view only (its preview and its export); the flat 2D view ignores it.
speedMultiplierNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses that processing is local and nothing is uploaded, that the returned link carries only the strokes, that playback is capped at 180 s, and it spells out the full export quota, watermark and plan gating (Free vs Premium including 4K/60fps). This is exactly the operational context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then the privacy note, the 180 s cap, and finally the plan and export rules - a logical order with little waste. The pricing and watermark clause is dense and could be tightened, keeping it just below top marks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with no output schema, the description covers what comes back (a link carrying strokes) and the preview/export split, which is the key unknown. The remaining gap is the missing speedMultiplier semantics and the unexplained mechanism for invoking the export, given no export argument exists in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 92%, so the enum parameters (pen, aspect, detail, background, camera angles, density) are already well documented and the description correctly needs no restatement. It adds only the 3D-versus-2D camera caveat implicitly and says nothing about speedMultiplier, which is the one parameter undocumented in both places, so it falls just short of full compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource - it paints a local PNG/JPEG as a Todrawn Scribe drawing, underpaint then pen strokes then video replay. The local-image input distinguishes it from the text-oriented siblings such as scribe_create_drawing without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives useful context that previewing is free and accountless while exporting an MP4 requires a free account with a 5-per-UTC-day cap, which implies a preview-then-export workflow. But it never states when to choose this over scribe_create_drawing or scribe_create_video, and the schema has no export parameter, so how an agent actually triggers the paid export is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.