Skip to main content
Glama

eye_color

Change iris color without altering the whites, optionally applying one of 16 Genesis 9 iris images or separate left/right tints for heterochromia.

Instructions

Changes iris color only (not the whites): a color tint, and on Genesis 9 one of its 16 iris images. For a whole new eye look, eye material presets also work (content_search).

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": {
      "figure": "<figure>"
    },
    "name": "eye_color"
  }
}

Input Schema

NameRequiredDescriptionDefault
eyesNoGenesis 9 can color each eye (heterochromia).both
irisNoGenesis 9 only: iris image 1-16 (1 hazel, 2 grey-brown, 3 light grey, 4 amber, 5 dark brown, 6 gold, 7 pale grey-blue, 8 hazel-gold, 9 grey-green, 10 blue-grey, 11 violet fantasy, 12 blue with gold, 13 blue, 14 grey freckled, 15 green, 16 light brown).
colorNoIris color; the whites of the eyes stay white.
figureYesFigure label.
removeNoTake the tint off.
strengthNoOpacity of the tint.
keep_irisNoTint the current iris instead of switching to light grey (3) first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish this is a non-destructive, local mutation, so the description's job is to add scope detail — and it does, clarifying that the sclera is untouched and that the 16-image iris option is Genesis 9-only. It does not explain side effects such as the implicit reset to light grey iris before tinting (that lives only in the schema) or failure modes for non-Genesis 9 figures using the iris parameter.

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?

Two compact sentences with the scope constraint front-loaded and the alternative routing at the end. Every clause carries information; nothing is restated from the schema or title.

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 7-parameter mutation tool with full schema coverage and safety annotations, the description supplies the essential framing: what changes, what does not, the Genesis 9 restriction, and where to go for a broader effect. Remaining gaps — figure-preparation prerequisites and interaction between simultaneous color/iris/remove arguments — are modest.

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 description coverage is 100%, including the full 1-16 iris enumeration, color format, strength range, and the keep_iris reset behavior, so baseline is 3. The description reinforces but adds nothing new about individual parameters — the Genesis 9 constraint it mentions is already stated in the 'iris' parameter description.

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 and resource ('Changes iris color'), immediately bounds the scope ('only (not the whites)'), and names the two mechanisms — a color tint and, on Genesis 9, one of 16 iris images. An agent can tell this apart from eye-material or gaze tools without opening the schema.

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?

Gives explicit routing advice for the adjacent use case: for a whole new eye look, use eye material presets via content_search. It stops short of naming when this tool is the wrong choice for other goals (e.g., gaze direction, which belongs to eyes_look_at), so it is clear but not exhaustive.

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