Claude Imagine

Convert Image to SVG

vectorize_image

Destructive

Convert an existing raster image (PNG, JPG or WebP) into an editable SVG vector file by tracing it, for 2 credits. Works best on logos, icons, stickers and flat illustrations; photos turn into many small shapes. Pass the full-resolution URL of an earlier result or any public image. To make an SVG from a description, first generate_image a flat design on a plain background (gpt-image-2.6 renders lettering well), then convert that URL.

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_url": "<image_url>"
    },
    "name": "vectorize_image"
  }
}

Input Schema

Name	Required	Description	Default
`image_url`	Yes	Public URL of the image to convert, normally the full-resolution URL from generate_image or edit_image
`max_credits`	No	Budget cap in credits, when the person stated one. If the exact cost of this call is above it, nothing is started and the reply lists what fits.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations, it discloses the concrete credit cost (2), the open-world dependency on a reachable public URL, and quality expectations by input class. It doesn't elaborate on what the destructiveHint implies (e.g. that a failed or poor trace still consumes credits or overwrites nothing), so a small gap remains.

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 conversion and cost, then suitability, then input sourcing, then the alternative workflow. Four sentences with little waste, though the parenthetical model name in the last sentence is marginally more detail than an agent needs to select the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with a fully documented schema and no output schema, the description covers cost, input sourcing, expected output form (editable SVG), input suitability, and the alternate path. Nothing an agent needs in order to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: image_url must be a full-resolution URL of an earlier result or any public image, and mentions that a prior generate_image output is the usual source. max_credits behavior is left entirely to the schema, which is acceptable.

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 and transformation (trace raster PNG/JPG/WebP into an editable SVG) and names the exact credit cost. This is clearly distinct from generate_image and edit_image, which create imagery rather than vectorize it.

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 when-to-use (logos, icons, stickers, flat illustrations), when-not (photos turn into many small shapes), and a step-by-step alternative route for text-described SVGs that names the sibling generate_image and the model to use. Nothing is left to inference.

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

All Claude Imagine 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?