Skip to main content
Glama

kernelcad

by com.kernelcad

Trace Outline from Image

trace_from_image

Use this when you need to trace features from a reference photo into waypoints. Trace pixel-space features from a reference photo into normalized [0..1] waypoints the agent can map to mm via a known scale anchor and feed to path().spline / path().nurbsSegment. Three backends are dispatched behind the scenes: opencv (deterministic; uniform-bg silhouette only), vision-llm (Claude vision; named points/cluttered backgrounds; caller-supplied ANTHROPIC_API_KEY), and hybrid (opencv silhouette + LLM-labeled named points). Default backend is auto — the tool picks based on the image's corner-color stddev. Accuracy honesty: opencv contour is geometrically exact; vision-LLM is typically 5–10% off on dense landmarks. Per-feature confidence is reported. Caller pays for any vision-LLM API spend via their own ANTHROPIC_API_KEY. Pair with the kernelcad-trace-from-image skill for the conversion-to-mm pipeline.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNoOptional free-text hint forwarded to vision-LLM backends (e.g. "a pair of eyewear; trace the upper brow only").
backendNoForce a specific backend; default `auto` routes by corner-color stddev.
featuresNoFeatures to trace. Defaults to a single { label: "silhouette", kind: "silhouette" } when omitted.
imageUrlYesURL or path to the reference image. Supports file://, http(s)://, data:image/...;base64,..., or a bare filesystem path.
maxWaypointsPerFeatureNoCap on waypoints per feature. Defaults to 12 (suitable for medium-inflection outlines).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
featuresYesTraced features with normalized [0..1] waypoints + confidence.
imageDimsYesPixel dimensions [width, height] of the source image.
diagnosticsYes

TDQS

A4.5/5.0
Behavior5/5

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

The description discloses multiple behavioral traits beyond annotations: three backends with dispatching logic, accuracy honesty (opencv exact, vision-LLM 5-10% off), caller pays for API, and per-feature confidence reporting. No contradiction with annotations (readOnlyHint=false, destructiveHint=false).

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?

The description is a single coherent paragraph with no wasted sentences. It is front-loaded with the core use case and then provides details. However, it is somewhat lengthy and could be slightly more concise, but each sentence adds necessary context.

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?

Given the tool's complexity (multiple backends, parameters, output schema exists), the description covers most aspects: input handling, backend selection, output format, accuracy, and cost implications. It could be improved by explicitly referencing the output schema structure, but the mention of 'confidence' and normalized waypoints suffices.

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 100%, so baseline is 3. The description adds value by explaining backend auto-selection, default features behavior, and the purpose of maxWaypointsPerFeature. It also clarifies how the 'hint' and 'region' parameters are used by vision-LLM backends, which the schema does not elaborate.

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 clearly states the tool's purpose: 'trace features from a reference photo into waypoints'. It specifies the output format (normalized [0..1] waypoints) and differentiates from sibling tools by focusing on image tracing for CAD, which none of the siblings cover.

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

Usage Guidelines4/5

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

The description explicitly says 'Use this when you need to trace features from a reference photo into waypoints' and provides guidance on backend selection (opencv, vision-llm, hybrid). It also mentions pairing with a skill. However, it does not explicitly state when not to use the tool or compare with alternatives, though siblings are not directly similar.

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

All kernelcad toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Tools are mostly distinct, with clear descriptions for each. However, there is some potential overlap between inspection tools like 'inspect' and 'mesh_summary', and between rendering tools 'render_preview' and 'get_latest_render', which could cause minor confusion.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern, making it predictable for an agent to infer functionality.

Tool Count2/5

44 tools is significantly higher than the typical well-scoped range of 3-15. While the domain is complex, the count feels excessive and could overwhelm an agent.

Completeness4/5

The tool set covers an extensive range of CAD operations including creation, inspection, rendering, export, and verification. Minor gaps exist, such as direct sketch editing tools, but overall it is comprehensive.

Resources