Skip to main content
Glama

ideogram_edit

Edit specific image areas with mask-based inpainting. Provide source image, mask (black=edit, white=keep), and prompt; output keeps source size.

Instructions

Edit specific areas of an image using mask-based inpainting. Requires source image, mask (black=edit, white=keep), and prompt; takes the style and character references, style codes, preset and palette (no exact resolution: inpaint keeps the source size).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maskYesLocal file path of the mask image (black = regions to edit, white = keep)
seedNoReproducibility seed
imageYesLocal file path of the source image to edit
promptYesDescription of desired changes
num_imagesNoNumber of variations (1-8, default: 1)
style_typeNoVisual style (the API default is GENERAL when omitted)
style_codesNo8-character hexadecimal style codes from Ideogram
magic_promptNoAuto-enhance prompts (default: AUTO)
style_presetNoA named style preset as Ideogram lists them
color_paletteNoA preset palette by name, or explicit colours with weights (not both)
rendering_speedNoSpeed/quality tradeoff (default: DEFAULT)
style_reference_imagesNoLocal image files whose style the result follows (up to 3, 25 MB each)
character_reference_maskNoGrayscale mask of the character reference (same dimensions); needs character_reference_image
character_reference_imageNoLocal image file of a character to keep consistent (one image; Ideogram bills character references at its own rate)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.2.0
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / character_reference_image
      Added value: +{
      +  "description": "Local image file of a character to keep consistent (one image; Ideogram bills character references at its own rate)",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / character_reference_mask
      Added value: +{
      +  "description": "Grayscale mask of the character reference (same dimensions); needs character_reference_image",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / color_palette
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "name": {
      +          "description": "A preset palette",
      +          "enum": [
      +            "EMBER",
      +            "FRESH",
      +            "JUNGLE",
      +            "MAGIC",
      +            "MELON",
      +            "MOSAIC",
      +            "PASTEL",
      +            "ULTRAMARINE"
      +          ],
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "name"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "members": {
      +          "description": "Explicit colours, most dominant first",
      +          "items": {
      +            "additionalProperties": false,
      +            "properties": {
      +              "color_hex": {
      +                "description": "The colour, #RRGGBB",
      +                "pattern": "^#[0-9A-Fa-f]{6}$",
      +                "type": "string"
      +              },
      +              "color_weight": {
      +                "description": "Its share of the palette (0.05-1)",
      +                "maximum": 1,
      +                "minimum": 0.05,
      +                "type": "number"
      +              }
      +            },
      +            "required": [
      +              "color_hex"
      +            ],
      +            "type": "object"
      +          },
      +          "maxItems": 10,
      +          "minItems": 1,
      +          "type": "array"
      +        }
      +      },
      +      "required": [
      +        "members"
      +      ],
      +      "type": "object"
      +    }
      +  ],
      +  "description": "A preset palette by name, or explicit colours with weights (not both)"
      +}
    • changedInput schema / properties / mask / description
      Previous value: -"Local file path of the mask image (black=edit, white=keep, min 10% black)"New value: +"Local file path of the mask image (black = regions to edit, white = keep)"
    • addedInput schema / properties / style_codes
      Added value: +{
      +  "description": "8-character hexadecimal style codes from Ideogram",
      +  "items": {
      +    "pattern": "^[0-9A-Fa-f]{8}$",
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / style_preset
      Added value: +{
      +  "description": "A named style preset as Ideogram lists them",
      +  "maxLength": 100,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / style_reference_images
      Added value: +{
      +  "description": "Local image files whose style the result follows (up to 3, 25 MB each)",
      +  "items": {
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 3,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • changedInput schema / properties / style_type / description
      Previous value: -"Visual style (default: AUTO)"New value: +"Visual style (the API default is GENERAL when omitted)"
  2. First observedv1.0.3

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 burden and does disclose useful behavior: mask semantics, required inputs, and that inpainting keeps the source resolution. However, it omits return format, side effects, auth/cost context, and other operational traits an agent would need for a mutation-style image edit.

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?

The description is front-loaded with the core purpose and avoids filler. It is somewhat dense with semicolons and parentheticals, but every clause contributes relevant information.

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

Completeness3/5

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

For a 14-parameter tool with no annotations and no output schema, the description is adequate but incomplete: it does not explain what the tool returns or how many images/variations are produced. The rich input schema covers parameters, reducing the burden, but output and operational context remain gaps.

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 schema already documents all 14 parameters in detail. The description summarizes optional style/character inputs and adds the resolution caveat, but adds little parameter-level meaning beyond what the structured schema provides.

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?

The description states a specific verb and resource: 'Edit specific areas of an image using mask-based inpainting.' This is clear and method-specific, distinguishing it practically from upscale/reframe/background-replacement siblings, but it does not explicitly name or compare against any sibling tool.

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?

Usage is implied by the mask-based inpainting method and the listed required inputs (source image, mask, prompt), but there is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The agent can infer the context but is not routed between this and siblings.

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