Skip to main content
Glama

Seamless pattern / texture (Pattern AI)

luw_generate_pattern

Generate a tileable, repeating pattern or texture from a text prompt—tiles, wallpaper, fabric, terrazzo, wood, or stone—so the design repeats cleanly across any surface.

Instructions

Luw.ai Pattern AI: generate a seamless, tileable pattern or texture — tiles, wallpaper, fabric, terrazzo, wood, stone — ready to repeat across a surface. Costs 1 credit.

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": "luw_generate_pattern"
  }
}

Input Schema

NameRequiredDescriptionDefault
sizeNo512 for a small tile; leave it out for the full size. aria: 1024 px small, 2048 px full; symphony: 512 px small, 1024 px full.
imageNoOptional reference image (public https:// link or data: URI; the local npx server also accepts a file path).
engineNoLuw.ai model: aria (default) or symphony (Symphony-3).
formatNoOutput image format.
promptYesThe pattern, e.g. "blue and white Moroccan zellige tiles".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.3.18
    • removedInput schema / properties / enhance_prompt
      Removed value: -{
      -  "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / image / description
      Previous value: -"Optional reference image (https:// URL, local file path, or data: URI)."New value: +"Optional reference image (public https:// link or data: URI; the local npx server also accepts a file path)."
    • removedInput schema / properties / size / anyOf
      Removed value: -[
      -  {
      -    "const": 512,
      -    "type": "number"
      -  },
      -  {
      -    "const": 768,
      -    "type": "number"
      -  },
      -  {
      -    "const": 1024,
      -    "type": "number"
      -  }
      -]
    • changedInput schema / properties / size / description
      Previous value: -"Output size in px. aria: 512 or 768 (default); symphony: 512 or 1024 (default)."New value: +"512 for a small tile; leave it out for the full size. aria: 1024 px small, 2048 px full; symphony: 512 px small, 1024 px full."
    • addedInput schema / properties / size / exclusiveMinimum
      Added value: +0
    • addedInput schema / properties / size / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / size / type
      Added value: +"integer"
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds genuinely new behavioral context beyond them: the 1-credit cost and the seamless/tileable output guarantee. It stops short of explaining whether the call is synchronous or requires polling another tool for the result.

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?

Two short clauses: the capability statement first, the cost second — front-loaded and waste-free. The pattern-family list is slightly enumerative but does useful scope-setting work by signalling what kinds of textures qualify.

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 5-parameter generation tool with full schema coverage and no output schema, the description covers the essential unknown — credit cost — and the defining property of the output. What remains unaddressed is the retrieval path for a non-idempotent, open-world generation call, which costs it a point.

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 every parameter (size, image, engine, format, prompt) already carries its own documentation, including engine-specific pixel sizes and the enum values. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'generate a seamless, tileable pattern or texture' — and enumerates concrete pattern families (tiles, wallpaper, fabric, terrazzo, wood, stone). The output artifact is unmistakable and inherently distinct from generic image generation, though no sibling is named explicitly.

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?

Usage is only implied: an agent can infer 'use this when you need a repeating surface texture' from the resource description. There is no explicit when-to-use condition, no when-not, and no pointer to alternatives such as a general image generator or expansion tool.

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