Chorono

by codie1982

Overview Schema Source Related Servers Discussions Admin

add_spline

Create editable spline primitives such as circles, ellipses, rectangles, lines, arcs, donuts, ngons, and stars with geometry parameters when you need vector paths with points and handles.

Instructions

Create an editable spline primitive (circle/ellipse/rectangle/line/arc/donut/ngon/star). Use over add_layer shapes when the user wants an editable vector path (points/handles). Each kind takes its own geometry params (radius, sides, angles…).

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": {
      "id": "<id>",
      "kind": "<kind>"
    },
    "name": "add_spline"
  }
}

Input Schema

Name	Required	Description
`x`	No	Layer x position
`y`	No	Layer y position
`id`	Yes	Unique layer id
`x1`	No	line start x
`x2`	No	line end x
`y1`	No	line start y
`y2`	No	line end y
`kind`	Yes	Primitive kind
`name`	No	Display name
`sides`	No	ngon side count
`width`	No	rectangle width
`height`	No	rectangle height
`points`	No	star point count
`radius`	No	circle / arc / donut(outer via outerRadius) / ngon radius
`radiusX`	No	ellipse x radius
`radiusY`	No	ellipse y radius
`endAngle`	No	arc end angle (deg)
`fillColor`	No	Fill hex (closed shapes)
`requestId`	No
`roundness`	No	ngon/star corner roundness 0–1
`sessionId`	No
`startAngle`	No	arc start angle (deg)
`innerRadius`	No	donut/star inner radius
`outerRadius`	No	donut/star outer radius
`strokeColor`	No	Stroke hex
`strokeWidth`	No	Stroke width px
`cornerRadius`	No	rectangle corner radius
`expectedRevision`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A4.3/5.0

Behavior3/5

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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description adds some value by noting the result is an editable path rather than a baked shape. However, it never says the layer is added to the active scene/session, whether the operation is undoable, or what expectedRevision/requestId/sessionId control even though these imply concurrency and session targeting. For a 28-param mutation tool that is a meaningful omission.

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

Conciseness5/5

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

Three short sentences: what it creates, the kind list, the sibling rule, then the per-kind param caveat. Front-loaded with zero filler and no repetition of schema content.

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

Completeness3/5

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

For a tool with 28 parameters, 2 required, no output schema, and kind-dependent geometry, the description covers the what and the why but not the operational mechanics. It does not state which params each kind requires, nor what expectedRevision/sessionId/requestId do, so an agent must read the schema closely to call it correctly.

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 89%, so the baseline is 3, and the description earns an extra point by telling the agent that geometry params are kind-dependent (radius, sides, angles…), which prevents blind enumeration of all 28 properties. It stops short of mapping each kind to its specific params, so it is helpful framing rather than full semantics.

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?

States a specific verb+resource (create an editable spline primitive) and enumerates the eight supported kinds, so the agent knows exactly what it produces. It also explicitly positions itself against add_layer shapes, making the boundary between the two siblings visible without opening schemas.

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

Usage Guidelines5/5

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

Gives an explicit selection rule: use this over add_layer shapes when the user wants an editable vector path with points/handles. The alternative and the condition that selects it are both named, leaving nothing to inference.

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

Deploy Server