01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→93, token cost up 1%, unconfirmed writes 0%→0%.
Category breakdown
Where the score comes from.
Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.
02Legibility
29.8 / 30
03Economics
14.1 / 20
04Discoverability
19.7 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
Description evidence
Defects and rewrites.
1 defect found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.
| Tool | Defect types | Suggested rewrite |
|---|---|---|
render_svg |
params_unexplained |
Render animated SVG from JSON config. AI controls all design parameters. **canvas (required):** {"width":800,"height":600,"viewBox":"0 0 800 600","background":"#ffffff"} — width/height are numbers or numeric strings in px and set the rendered SVG's outer dimensions; viewBox is an optional "minX minY width height" string setting the internal coordinate system (defaults to matching width/height at origin 0,0); background is an optional hex color (or "none") used as the canvas backdrop fill. **Workflow:** render_svg returns a PNG preview of the result plus an artifact id — critique the image, revise the config, render again. Iterate at least 3 times before finalizing. The SVG text stays on the server: pass the artifact id to save (and to preview for a different width). **output options (response shape, not content):** {"svg":false,"preview":true,"previewWidth":800,"minify":false,"frames":4} — all optional. minify:true collapses whitespace in the stored/saved SVG. frames:N (2-10) replaces the static preview with one filmstrip image sampling the CSS animations at N times — use it to verify motion (rotation direction, timing, easing) since a single preview only shows t=0. SMIL is not sampled. **elements (required array):** the shapes/content to render. Element types: rect, circle, ellipse, line, polyline, polygon, path, image, text, textPath, group, use, radial-group, arc-group, grid-group, scatter-group, path-group, parametric **Pattern groups** (use for repetitive designs): radial-group (circular: cx, cy, radius, count), arc-group (arc: cx, cy, radius, count, startAngle, endAngle), grid-group (matrix: cols, rows, colSpacing, rowSpacing), scatter-group (random: width, height, count, seed), path-group (along polyline: waypoints, count). Each takes ONE "child" element. The child is drawn at the local origin and, with rotateChildren true (the default), rotates so local +x points outward from the center: draw spokes, rays and petals long along the x axis, never the y axis, or they render as a chord ring. **Parametric curves** (fn field): rose, heart, lissajous, spiral, star, superformula, epitrochoid, hypotrochoid, wave. Size via "scale" field. Server computes coordinates. **defs (optional object):** gradients (linear/radial, SMIL animated stops), filters (presets: glow, neon, blur, drop-shadow, glitch, chromatic-aberration, noise, outline, inner-shadow, emboss + 5 more), clipPaths, masks, patterns (tile fills), markers (arrowheads: triangle, arrow, circle, square, diamond, bar; set markerStart/markerEnd:"id" on line/polyline/path, scales with strokeWidth). **animations (optional array):** CSS @keyframes via animations array. Set cssClass on element matching animation name. For transforms add transformBox="fill-box" transformOrigin="center". SMIL via smilAnimations on elements (animate, animateTransform, animateMotion). **Design guide (what makes output look good):** Pick one spacing unit (e.g. 8) and use multiples of it for every gap and margin; keep content clear of the canvas edges by at least 5% of the smaller dimension (the bbox audit reports overflow in px). Use at most 3 font sizes per design with clear jumps (e.g. 12/16/24). Body-size text needs 4.5:1 contrast against its background, 3:1 from 24px up (the contrast audit checks plain hex pairs). Text ink boxes are measured after every render; escaping or overlapping text comes back as a named design note. Motion: ease-out for entrances, ease-in-out for back-and-forth loops, linear only for continuous rotation or travel; 0.8-3s durations read well for UI-scale loops. **Critical format rules:** - Gradient type must be "linearGradient" or "radialGradient" (not "linear"/"radial"). Each needs id, stops (array with offset 0-1, color). - Filter type must be "preset" with a "preset" field: {"type":"preset","id":"myGlow","preset":"glow","stdDeviation":8,"color":"#ff00ff"} - Keyframe offset: use "from"/"to" or percentage number 0-100 (not "0%"/"100%"). - Gradient stop and filter colors: hex only (#rrggbb or #rrggbbaa). Element fill/stroke accept '#rrggbb', 'none', or 'url(#id)' (hex is safest). - Every element needs "type" field. circle needs r, rect needs width+height, path needs d. **Field names that differ from raw SVG:** - text: string goes in "content" (not "text"): {"type":"text","x":100,"y":50,"content":"Hello","fontSize":24,"textAnchor":"middle"} - textPath: {"type":"textPath","pathId":"idFromDefsPaths","text":"..."} — here the field IS "text". - group: {"type":"group","children":[...]} — children are shapes/text/use only, no nested groups. - Pattern groups take ONE "child" element drawn at local origin (child uses cx=0/cy=0); set rotateChildren:false to keep text upright. **Returns:** a PNG preview image of the render plus an artifact id referencing the stored SVG (pure SVG XML, no JavaScript, CSS @keyframes + SMIL only); pass svg:true in output to also get the raw SVG text back. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field