MagicPixel

Improve prompt (active style)

enrich_prompt

Rewrite a short prompt into a fully-styled MagicPixel prompt using the brief of the account's active style (same as in-app Improve prompt). Does not spend AI generation credits; subject to daily enrich quota. Prefer get_style_profile / update_style_profile first when no style is active or its brief is empty. When generating more than one asset (Quantity / Quality), pass count so the rewrite is a diverse family brief instead of one locked design. Pass size so a 32px-or-smaller sprite gets a short, minimal rewrite.

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": {
      "prompt": "<prompt>"
    },
    "name": "enrich_prompt"
  }
}

Input Schema

Name	Required	Description
`mode`	No	"generate" expands a new-asset request (default); "edit" sharpens an edit instruction.
`size`	No	Sprite size in art pixels (the generate_pixel_art size). Pass it: at 32 or smaller the rewrite is kept short and minimal, the way a tiny retro sprite needs.
`count`	No	How many assets generate_pixel_art will produce from this prompt. Pass the Quantity/Quality count (>1) so enrichment writes a family brief instead of locking one silhouette. Omit or 1 for a single asset.
`prompt`	Yes	Short user request to expand (e.g. "red knight shield"). Same cap as the in-app prompt box: longer text is trimmed to the first 1000 characters and the reply says so.
`variation`	No	Pass a higher number to request a visibly different rewrite of the same prompt.
`subject_category`	No	Optional subject hint for the enricher (character\|item\|building\|ui\|custom\|texture).

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 only give a generic safety profile (readOnly=false, destructive=false, openWorld=true), so the description usefully adds the cost model: no AI generation credits consumed, but a daily enrich quota applies. It also discloses a dependency (active style brief must be non-empty). What it omits is the shape of the result (a rewritten prompt string returned directly) and what happens when the quota is exhausted.

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?

Front-loaded with the core action and cost facts, then prerequisites, then parameter guidance — a sensible priority order with no filler sentences. It loses a point only because the count/size sentences largely duplicate the schema's own parameter descriptions.

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 six-parameter, no-output-schema tool, the description covers purpose, cost, prerequisite state, and the two most consequential parameters, which is close to complete. The remaining gap is that it never states the return value is the rewritten prompt text itself, leaving the agent to infer the response shape.

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%, so the schema already explains every parameter including the count, size, mode, and variation semantics. The description mostly restates the count and size rationale already present in the schema, and it never mentions mode or variation. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (rewrite) on a specific resource (a short prompt), names the output artifact (fully-styled MagicPixel prompt) and the mechanism (the account's active style brief). It also explicitly disambiguates from generation siblings by noting it does not spend AI generation credits, so an agent can tell it apart from generate_pixel_art or apply_with_ai 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 Guidelines5/5

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

Gives explicit routing: use get_style_profile / update_style_profile first when no style is active or its brief is empty. It also names the two conditional usage patterns (pass count when producing multiple assets, pass size for tiny sprites), which is the when-and-how guidance an agent needs.

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

All MagicPixel tools Inspect

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

Need Help?