Skip to main content
Glama
Sign In

MagicPixel

by art.magicpixel
OverviewDiscussionsAdmin

Update the active style

update_style_profile
Idempotent

Switch the account's active style and/or set its text. active_style picks one of the account's styles by name (get_style_profile styles) or "No style". brief replaces the active style's; with No style active it creates a new style (named by name) and make it active. Every generation uses the active style. Tell the user what you set; they can change it from the style picker in Create with AI.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "update_style_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName for the style a brief creates while No style is active (default "My style"). Ignored otherwise.
briefNoThe game's world and look in plain sentences (setting, cast, materials, outlines, light, key colours), at most 500 characters. Sizes and rules are cut; name the camera in each prompt. "" clears it.
active_styleNoName of one of the account's styles to make active, or "No style". Adding MagicPixel styles happens in the app (magicpixel.art/styles).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare this is a non-destructive, idempotent write, so the description needn't re-establish safety. It adds real behavioral context instead: that brief overwrites existing style text, that a new style may be created and made active, that the setting affects all subsequent generation, and that the user can revert via the style picker. Minor grammar slippage ('brief replaces the active style's;') slightly obscures the overwrite clause.

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?

It is front-loaded with the core action and then proceeds in the order an agent would reason: active_style, brief, creation fallback, side effects, user communication. The one flaw is the elliptical possessive in 'replaces the active style's;', which forces the reader to infer 'text'.

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 three-parameter write with full schema coverage, no nested objects, and no output schema, the description covers purpose, parameter interplay, side effects on generation, and the required user-facing follow-up. The only gap is the slightly broken overwrite sentence, which is a clarity issue rather than a missing behavior.

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 100%, so the per-parameter text already carries the format details. The description still adds cross-parameter behavior that the schema does not: brief replaces the active style's text, and name is only meaningful when brief triggers creation while No style is active. That interaction is the highest-value thing an agent needs and it is stated plainly.

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 first sentence names a concrete verb and resource ('Switch the account's active style and/or set its text') and the rest disambiguates the two operations. It explicitly points to get_style_profile as the source of valid style names, so an agent can tell this apart from the read-side style tools without opening a 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?

It states the conditions under which each path applies: active_style selects by name or 'No style', and brief creates-plus-activates a style only when No style is active. It also explains the downstream effect ('Every generation uses the active style') and tells the agent to inform the user. It stops short of explicit when-not guidance or failure cases, but the conditional logic covers the practical decisions.

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

All MagicPixel toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources