Detect circles, rectangles, triangles, and polygons from image contours, then optionally create a trace layer using a confidence threshold.
Detect geometric shapes (circles, rectangles, triangles, polygons) from contours.
| Name | Required | Description | Default |
|---|---|---|---|
| sourceId | No | Reference image asset ID (default: current canvas). | |
| createLayer | No | Create a trace layer (default: true). | |
| minConfidence | No | Minimum confidence 0–1 (default: 0.5). |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It says nothing about the fact that it likely creates a trace layer (the createLayer parameter defaulting to true implies a canvas mutation), whether it overwrites or adds geometry, whether the source is a raster image or existing contour paths, or what is returned. For a mutation-capable tool with zero annotation coverage this is a real gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with zero filler; the shape list is useful enumeration. It is slightly under-sized for a tool with three parameters and no annotations, but nothing in it is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations, no output schema, and a dense family of sibling trace tools, the description should explain source behavior, output (vector paths vs shapes vs new layer), and how results are affected by createLayer/minConfidence. None of that is present, leaving the agent to guess at side effects and results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: sourceId, createLayer, and minConfidence all have documented defaults and types. The description adds no additional parameter meaning (e.g. what confidence means for shape detection or what sourceId accepts), so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Detect') and resource ('geometric shapes: circles, rectangles, triangles, polygons') with the input condition ('from contours'). An agent knows what the tool produces, but among nine sibling trace_* tools there is no explicit differentiation from design_trace_contours or design_trace_edges, which is the main ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no mention of the many alternative trace tools (design_trace_lines, design_trace_regions, design_trace_splines), and no prerequisites such as needing an existing contour or raster source. The agent must infer selection purely from the one-line purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.