Skip to main content
Glama

Recreate Design

recreate

Convert design images or analyze_design JSON specs into production-quality HTML, React, or Tailwind code, with responsive layouts and accessibility fixes.

Instructions

Recreate a design as production-quality code. Provide an image (path or URL), a JSON spec from analyze_design, or both. Returns code only.

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": "recreate"
  }
}

Input Schema

NameRequiredDescriptionDefault
specNoJSON spec returned by analyze_design
imageNoLocal file path or http(s) URL of the design image
formatNoOutput code formathtml
responsiveNoMake the result mobile, tablet and desktop friendly
fix_accessibilityNoFix contrast, tap-target and semantic issues

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully clarifies 'Returns code only', signaling no file writes or side effects. But it omits what happens with no inputs (0 required params), whether code is returned inline vs. saved, and any size/rate limits — meaningful gaps for a generation tool.

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?

Three short sentences, front-loaded with the core action, then input options, then return behavior. No filler or redundancy.

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?

No output schema exists, and the description does the essential job of stating the return is code only. Combined with 100%-covered params, an agent can call it correctly. The main omission is behavior when neither image nor spec is given, which matters given zero required parameters.

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 all five parameters including defaults (responsive, fix_accessibility) and the format enum are already documented. The description only restates that image can be a path or URL and spec comes from analyze_design, adding little beyond the schema; baseline 3 is appropriate.

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: 'Recreate a design as production-quality code.' The 'production-quality code' qualifier clarifies the output nature and the reference to analyze_design as a possible input source distinguishes the typical workflow. It doesn't clearly differentiate from siblings like 'reimagine', but the core purpose is unambiguous.

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 says to provide 'an image (path or URL), a JSON spec from analyze_design, or both', which gives implicit guidance on input combinations and the ordered relationship with analyze_design. However, it gives no explicit when-to-use versus alternatives (e.g. reimagine) and no guidance on what to do when neither input is supplied, despite zero required parameters.

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