Skip to main content
Glama

generate_game_assets

Draw a matching set of 2D game assets from one description: 8 items, 8 icons, 4 character designs, 4 seamless tiles or an 8-piece UI kit. Returns a download link to the raw sheet (on a flat green or magenta key color) and the exact command that cuts it into transparent PNGs, a sprite sheet and a JSON atlas in the project. Takes 30-90 seconds. Free tier: 3 sets per day per IP address.

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": {
      "kind": "<kind>",
      "description": "<description>"
    },
    "name": "generate_game_assets"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesWhat to make.
styleNopixel
descriptionYesWhat the set contains, e.g. "healing potions and elixirs in glass bottles". Your own designs only: no other studios' characters, no real people.
style_reference_urlNoOptional https URL of a PNG/JPG/WebP from the game (under 4 MB). The set is drawn in that art style.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does so well: it discloses the return payload (download link to a raw sheet on a flat green or magenta key color plus the exact command that cuts it into transparent PNGs, a sprite sheet and a JSON atlas), the 30-90 second runtime, and a per-IP rate limit. Remaining gaps are that it doesn't say whether the call blocks for the full 30-90s or returns a job handle, and it doesn't describe failure modes.

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?

Four dense sentences in a deliberate order: what it makes, what it returns, how long it takes, what it costs. The per-kind counts are compressed into a single clause and no sentence is redundant.

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?

With no output schema and no annotations, the description steps up: it explains the return artifacts, the key-color background, the post-processing command, latency and quota — everything an agent needs to plan a call and handle the result. The only shortfall is not stating whether the invocation is synchronous or requires polling.

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 coverage is 75%, just under the threshold where the schema alone would suffice, and the description does add real meaning the enum lacks by stating the count produced per kind (8 items, 4 characters, 4 tiles, 8-piece UI kit). It says nothing about `style` behavior or how `style_reference_url` influences the output beyond what the schema already states.

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?

Opens with a specific verb and resource ('Draw a matching set of 2D game assets from one description') and immediately enumerates the five output shapes (8 items, 8 icons, 4 characters, 4 tiles, 8-piece UI kit) that map to the `kind` enum. An agent knows exactly what it gets and can distinguish this from the only sibling, get_free_quota.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The description implies when the tool is appropriate (producing a coherent, matched asset set) and supplies practical gating context via the free-tier limit of 3 sets per day per IP, which is directly relevant given the get_free_quota sibling. However, it never explicitly routes the agent to get_free_quota to check remaining quota, and it gives no when-not-to-use guidance or prerequisites.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources