Skip to main content
Glama

Cross Stitch Pattern Maker

Turn a photo into a cross stitch pattern

create_cross_stitch_pattern

Turn a photo into a cross stitch pattern preview with real DMC thread colours. Returns a preview image of the stitched result, the thread list (DMC numbers and stitch counts), the stitch count and the finished size. Give exactly one of image_url, photo_id or image_base64. Show the preview image to the person. If they want to stitch it for real, offer the custom kit (order_custom_kit).

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": "create_cross_stitch_pattern"
  }
}

Input Schema

NameRequiredDescriptionDefault
kit_sizeNoKit size in inches, width x height, e.g. "12x16". Orientation is matched to the photo automatically. Call get_kit_prices to see every size. Default: chosen from the photo shape.
photo_idNoPhoto code (ph_...) from the upload page.
image_urlNoPublic http(s) URL of a JPG or PNG photo.
max_colorsNoMaximum number of DMC thread colours. Default 30.
fabric_countNoAida fabric count (stitches per inch). 14 = more detail, 11 = bigger stitches, easier for beginners. Default 14.
image_base64NoJPG or PNG bytes as base64 (a data: URL is also accepted). Max 10 MB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare non-destructive, open-world, non-idempotent, non-read-only, so the safety profile is covered; the description adds genuine value by enumerating what comes back (preview image, thread list with DMC numbers and stitch counts, stitch count, finished size) and by telling the agent to display the preview. It says nothing about whether the pattern is persisted server-side or about cost/regeneration behavior, which matters given readOnlyHint=false.

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 short sentences: what it does, what it returns, the input constraint, and the next-step handoff. The outcome is front-loaded and no sentence is filler.

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, the description compensates well by listing the returned artifacts, and the 6-param schema is fully documented. Missing only side-effect clarity (does creating a pattern store anything or count against a quota) and failure behavior for a bad URL, which are minor for a preview generator.

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 parameters are already documented (kit_size, max_colors, fabric_count defaults and enums). The description still adds a constraint the schema cannot express: exactly one of the three image inputs must be supplied, which prevents an agent from sending none or several. It adds nothing further on kit_size orientation or color limits beyond what the schema 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?

The description opens with a specific verb+resource ('Turn a photo into a cross stitch pattern preview') and immediately scopes it with 'preview' plus 'real DMC thread colours', so it is clearly a generator, not an order or upload tool. An agent can distinguish it from order_custom_kit and get_photo_upload_link without opening a schema.

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

Usage Guidelines4/5

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

It gives a hard input rule ('Give exactly one of image_url, photo_id or image_base64') and an explicit downstream handoff ('If they want to stitch it for real, offer the custom kit (order_custom_kit)'). It does not route the agent to get_photo_upload_link when the user has no photo yet, which is a real gap given photo_id comes 'from the upload page'.

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.