Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

draw_eyes

Redraws a character's eyes frame by frame to animate expressions like gaze direction, blinks, sleepy or angry lids, and smiles with per-frame control.

Instructions

Redraw a character's eyes, frame by frame, to give it an expression: where it looks, blinks, sleepy or angry lids, a smile. eyes lists each eye's socket, the area INSIDE its ring, in canvas pixels: {"x": 44, "y": 27.5, "rx": 6.5, "ry": 6.3}, optionally "pupil": [rx, ry] (about half the socket by default), "look_scale" (0.7 for a far eye in a 3/4 view) and "inner": "left"|"right" (the side toward the beak or nose, for brows). Measure sockets with look first. keys, one per frame (frames are made as needed): {"frame": 1, "look": [dx, dy], "lid": 0..1, "arc": 0..1, "brow": -0.6..0.6, "smile": 0..0.6, "closed": false, "ms": 120}. lid lowers the upper lid; arc curves it (relaxed, happy); brow > 0 slants it down toward the inner side (angry, focused), < 0 the other way (worried, sad); smile pushes up a lower lid; closed shuts the eye. Expression is easy to misread: when unsure, draw 3-4 options and ask. Colours come from the eyes already there; pass the returned style back on every sprite of the same character so all its eyes match. The area round each eye is repainted in skin colour. One undo step. Headless: pass file.

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": {
      "eyes": "<eyes>"
    },
    "name": "draw_eyes"
  }
}

Input Schema

NameRequiredDescriptionDefault
eyesYes
fileNo
keysNo
layerNo
styleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations carry only a title, so the description bears the full burden and does it well: it discloses that the area around each eye is repainted in skin colour (an overwrite side effect), that the operation costs exactly one undo step, that colours are inherited from existing eyes, and that frames are created as needed. These are the facts an agent needs before mutating a sprite.

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?

Purpose is front-loaded, then measurement, then the keys schema, then behavioural caveats — a sensible progression with no filler sentences. It is dense and long, but every clause carries parameter or behaviour information; the inline literals make it scannable rather than rambling.

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?

There is no output schema, and the description only hints at the response by referring to 'the returned ``style``'. For a 5-parameter, nested-object tool with zero schema descriptions, the prose is otherwise complete enough to call the tool correctly, with the missing ``layer`` parameter the main omission.

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 description coverage is 0%, so the prose must carry the parameters, and it does: it fully documents the ``eyes`` object fields (x, y, rx, ry, pupil, look_scale, inner), the ``keys`` per-frame fields with ranges and semantics (lid 0..1, arc, brow -0.6..0.6, smile, closed, ms), plus ``style`` and ``file``. The only gap is ``layer``, which is never mentioned.

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 opening states a specific verb and resource: redraw a character's eyes frame by frame to give an expression. It then enumerates the expressive dimensions (look, blink, lids, smile) so the agent knows exactly what the tool produces, distinct from generic drawing siblings like draw_ellipse.

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?

Explicit prerequisites and workflow are given: measure sockets with ``look`` first, draw 3-4 options and ask when an expression is ambiguous, and reuse the returned ``style`` across every sprite of the same character. It also names the headless path via ``file``. This is when-to-use plus how-to-sequencing, not just what-it-does.

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