Skip to main content
Glama

render_liquid_glass

Render a pixel-perfect Liquid Glass icon preview matching iOS 26 quality using Apple's ictool.

Instructions

Render a pixel-perfect Liquid Glass preview using Apple's ictool. Produces the exact same rendering as iOS 26. Requires Icon Composer.app installed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
zoomNoZoom level — icon size relative to canvas (1.0 = full canvas, 0.5 = half size)
scaleNoScale factor (1x, 2x, 3x)
widthNoOutput width in pixels
heightNoOutput height in pixels
platformNoTarget platformiOS
canvas_bgNoSimple preset canvas background
renditionNoAppearance renditionDefault
tint_colorNoTint hue (0-1) for tinted renditions
bundle_pathYesPath to .icon bundle
light_angleNoLight angle in degrees (0-360). Controls direction of specular highlights and shadows.
output_pathYesOutput path for the PNG file
apple_presetNoApple Icon Composer preset background (overrides canvas_bg)
return_imageNoReturn the rendered image inline as base64 (default true)
tint_strengthNoTint strength (0-1) for tinted renditions
canvas_bg_colorNoCustom hex color for canvas background
canvas_bg_imageNoPath to custom background image

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.0
    • addedInput schema / properties / return_image
      Added value: +{
      +  "default": true,
      +  "description": "Return the rendered image inline as base64 (default true)",
      +  "type": "boolean"
      +}
  2. First observedv1.0.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description must carry the behavioral disclosure. It reveals the tool uses ictool and requires Icon Composer, but omits details on error handling, performance implications, or what happens if prerequisites are missing.

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?

The description is extremely concise with two sentences, front-loading the core purpose and key prerequisite. Every sentence adds value without redundancy.

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?

Given 16 parameters and no output schema, the description covers the core function and prerequisite but lacks guidance on parameter interactions (e.g., tint vs renditions) or default behaviors.

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?

With schema description coverage at 100%, all parameters are documented in the schema. The description adds no additional parameter-level context beyond what the schema already provides.

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 description clearly states it renders a Liquid Glass preview using Apple's ictool, matching iOS 26 rendering. It distinguishes from sibling tools like create_icon or export_preview by specifying the exact rendering engine and output quality.

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?

The description mentions a prerequisite (Icon Composer.app) and implies use for exact iOS 26 previews, but does not explicitly declare when to use alternatives like export_preview or set_glass_effects.

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