Skip to main content
Glama

Design to Prompt

design_to_prompt

Converts design images into ready-to-paste prompts for AI UI generators, image models, or developer handoff specs.

Instructions

Turn a design image into a ready-to-paste prompt for an AI UI generator (v0, Lovable, Bolt), an image model, or a developer handoff spec.

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": {
      "image": "<image>"
    },
    "name": "design_to_prompt"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesLocal file path or http(s) URL of the design image
targetNoui-generator

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does usefully disclose the return artifact ('ready-to-paste prompt'), but says nothing about whether the image is read locally from disk, latency or model cost, whether the call is purely read-only, or how the output differs per target beyond the target name itself.

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?

A single front-loaded sentence with no filler; the verb and outcome come first and the parenthetical examples add concrete value rather than padding.

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 two-parameter converter with no output schema and no annotations, the description covers the essential contract: image in, paste-ready prompt out, with three target modes. Remaining gaps are minor — expected prompt length/format and image input constraints are left to the schema.

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 only 50%, so the description must compensate. It does add meaning to the `target` enum by mapping each value to a concrete consumer (v0/Lovable/Bolt, image model, developer handoff spec), but adds nothing about the `image` parameter (formats, size limits, local vs URL handling) beyond what the schema description already states.

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+resource: converting a design image into a prompt, and names the three output flavors (UI generator, image model, dev handoff). It does not explicitly contrast with siblings like analyze_design, recreate, or reimagine, so an agent must infer that this is the 'produce a prompt' rather than 'describe/critique/rebuild' path.

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

Usage Guidelines2/5

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

The description indicates what the tool produces but gives no when-to-use or when-not guidance, and no alternatives are named. An agent facing analyze_design or recreate alongside this tool gets no signal about which to pick; only the target enum implies different downstream scenarios.

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