page_pixels
Renders an element as a digit luminance grid so an agent can inspect shapes, layout, and captcha gaps without a vision model.
Instructions
SUPERMAN GLASSES: render an element (canvas / img / background-image) as a compact luminance GRID of digits 0-9 the agent READS directly — see shapes, holes, object orientation, image layout WITHOUT a vision model. 0=black, 9=white. Captcha gaps appear as darker cells, upright skies are bright rows on top. Pass the ref from page_a11y. Returns JSON {w, h, grid:[rows of digits]}.
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": {
"session_id": "<session_id>",
"page_id": "<page_id>",
"ref": "<ref>"
},
"name": "page_pixels"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | Ref of the element to render (canvas / img / background-image). | |
| grid_h | No | Grid height in cells (default 21). | |
| grid_w | No | Grid width in cells (default 32). | |
| page_id | Yes | ||
| session_id | Yes |