Skip to main content
Glama

Edit design

edit_design

Change a design or the user's own photo in plain words: make the subject bigger, add a short text, a name or a date, add a frame, change colours or remove something. Use this for every change to a design (never regenerate the image yourself), then create_proof. Only that change is made. Creates a new design; the original is kept. Takes about 45 seconds.

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": {
      "design": "<design>",
      "instruction": "<instruction>"
    },
    "name": "edit_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
designYesDesign id (ont_...)
productNoProduct reference it will be printed on; the result then gets the shape of that product (e.g. wide for a mug), with text inside the printed area
instructionYesWhat should change
real_subjectNoOnly for a real, existing building, monument, bridge, windmill, church or recognisable place the user names: its name and town, e.g. 'Poldertoren Emmeloord'. The engine looks up a photo of it and draws the real one. Not for the user's own house, pet or people: ask for a photo.
reference_photoNoDesign id of a photo the user uploaded that shows what the subject really looks like (their dog, their house, or a photo of the building)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / real_subject
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 120,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only for a real, existing building, monument, bridge, windmill, church or recognisable place the user names: its name and town, e.g. 'Poldertoren Emmeloord'. The engine looks up a photo of it and draws the real one. Not for the user's own house, pet or people: ask for a photo.",
      +  "title": "Real Subject"
      +}
    • addedInput schema / properties / reference_photo
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Design id of a photo the user uploaded that shows what the subject really looks like (their dog, their house, or a photo of the building)",
      +  "title": "Reference Photo"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Adds behavior beyond the annotations: the change is scoped ('Only that change is made'), a new design is created while the original is kept (consistent with destructiveHint=false), and it takes about 45 seconds. The latency and copy semantics are exactly the extra context annotations cannot convey.

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?

A single front-loaded paragraph: verb and examples first, then the workflow constraint, then the side-effect and timing disclosure. Dense but every sentence carries information; minor cost is that multiple behavioral facts are packed into one run-on block.

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?

Covers the mutation semantics, non-destructiveness, and the follow-up call (create_proof) for a non-idempotent write tool with no output schema. It never says what comes back from the call (e.g. the new design id), which is the main remaining gap for chaining into create_proof.

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 the baseline is 3; product, real_subject and reference_photo are already well documented in the schema. The description only enriches the 'instruction' parameter with example phrasings and adds nothing for the other four.

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 ('Change a design or the user's own photo') and gives concrete example edits. It does not explicitly contrast with the sibling restyle_design, which also mutates a design, so differentiation is incomplete.

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?

Clear directive: 'Use this for every change to a design (never regenerate the image yourself), then create_proof' – it names the next step and forbids an alternative approach. It stops short of naming restyle_design or explaining when restyle_design is preferred.

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.

Resources