Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

draw_ellipse

Draw an ellipse on the Aseprite canvas using a center point and independent x/y radii, with optional fill and preview. Each call applies one undo step.

Instructions

Draw an ellipse centered at (center_x, center_y) with independent x/y radii. fill true fills it. One undo step. Headless: pass file.

preview true also returns a before/after picture of the canvas with the changed-pixel count and bbox.

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": {
      "center_x": "<center_x>",
      "center_y": "<center_y>",
      "radius_x": "<radius_x>",
      "radius_y": "<radius_y>",
      "color": "<color>"
    },
    "name": "draw_ellipse"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
fillNo
colorYes
previewNo
center_xYes
center_yYes
radius_xYes
radius_yYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations carry only a title, so the description must carry the behavioral burden, and it does add real value: "One undo step" discloses reversibility/atomicity, and the headless/``file`` note reveals a mode constraint. It still omits what ``color`` accepts, whether drawing outside canvas bounds is clamped or errors, and what happens on headless runs without a file.

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?

Four short sentences, front-loaded with the core operation, then option semantics, then side effects. Terse to the point of being telegraphic in places ("``fill`` true fills it"), but no sentence is padding.

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?

For a mutation tool with no safety annotations, the description covers undo cost, headless operation, and preview output, and an output schema exists so return values needn't be spelled out. The remaining hole is color format and boundary/error behavior, which matter for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description is the only source of parameter meaning. It explains ``fill``, ``file`` (headless), and ``preview`` behavior plus the geometry of center/radii, but the required ``color`` parameter gets no format guidance (hex, name, palette index?) and neither ``preview`` output shape nor defaults are fully pinned down.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ("Draw an ellipse") and adds geometric detail (center point, independent x/y radii) that implicitly separates it from the sibling draw_circle. It never names an alternative outright, so differentiation is inferable rather than explicit.

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

Usage Guidelines3/5

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

It gives conditional context for two modes: pass ``file`` when headless, and ``preview`` to get a before/after picture plus pixel count and bbox. There is no guidance on when to choose this over draw_circle or shape-approximation siblings, nor any stated prerequisites.

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

Deploy Server

Other Tools