Skip to main content
Glama

Metadata MCP Connector

Upload Image Creative

upload_image_creative

Upload images directly to Metadata platform library to create image creatives. Downloads images from provided URLs and uploads them to the platform. REQUIRED STEP IN AD CREATION WORKFLOW: This tool MUST be called between generate_brand_creative and create_update_image_ad. WORKFLOW INTEGRATION: This tool is part of the ad creation workflow and should be used: 1. BEFORE creating ads with create_update_image_ad (which requires imageLibraryId/creativeID) 2. IN COMBINATION with generate_brand_creative to create AI-generated images first, then upload them 3. When you need to upload existing images from external sources

            **COMMON WORKFLOWS:**
            - Upload existing images → Get imageLibraryId → Use in create_update_image_ad
            - Generate image with generate_brand_creative → Download generated image → Upload with this tool → Use in create_update_image_ad
            - Batch upload multiple creative assets for campaign preparation

            **IMPORTANT:** The returned image ID (imageLibraryId/creativeID) is REQUIRED when creating ads.
            Every ad needs a creative asset, so you must upload images first before calling create_update_image_ad.

            REQUIRED PARAMETERS:
            - images: Array of image URLs to upload

            IMAGE REQUIREMENTS:
            - URLs must be valid and publicly accessible
            - Supported formats: PNG, JPG, JPEG, GIF, WebP, and others
            - Images will be downloaded and then uploaded to platform
            - Filenames with spaces will have spaces replaced with underscores

            EXAMPLES:

            Single Image:
            upload_image([
                "https://my-bucket.s3.amazonaws.com/images/sample-image.png"
            ])

            Multiple Images:
            upload_image([
                "https://my-bucket.s3.amazonaws.com/images/logo.png",
                "https://example-assets.s3.us-west-2.amazonaws.com/photos/banner.jpg",
                "https://content-bucket.s3.eu-west-1.amazonaws.com/uploads/hero image.webp"
            ])

            RESPONSE FORMAT:
            Returns array of objects for each image:
            [
                {
                    "url": "https://original-url.com/image.png",
                    "name": "image.png",
                    "id": 12345,
                    "success": true
                },
                {
                    "url": "https://failed-url.com/bad.png",
                    "name": "bad.png",
                    "id": null,
                    "success": false,
                    "error": "Download failed: Connection timeout"
                }
            ]

            ERROR HANDLING:
            - If one upload fails, others will continue
            - Each result includes success status
            - Failed uploads include error message
            - Successful uploads include platform image ID

            USE CASES:
            - Upload creative assets before creating ads
            - Import images from external sources
            - Batch upload multiple campaign images
            - Migrate images from other platforms

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
namesNoOptional library name per image, positional against `images`. Pass one whenever you know what the creative is: without it the name is taken from the URL, which for a generated creative is an opaque key like `brand_creative_20260814_211126_66d8a83e.png` and leaves the user unable to tell their creatives apart in the library. Use `<brand-domain>-<channel>-<width>x<height>.png`, e.g. `stripe-com-linkedin-1200x1200.png`. A name MUST end in one of .jpg/.jpeg/.png/.gif/.mov/.mp4/.html/.pdf.
imagesYesArray of image URLs to upload to platform

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With readOnlyHint=false, the description correctly signals a mutating import operation and adds the download-from-URL mechanism, partial-failure behavior, success/failure response format, and filename underscore replacement. None of this repeats the annotations, and no contradictions exist.

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 long but highly structured, with clear sections, bolded workflow directives, examples, response format, and error handling. It has some redundancy (the intro sentence, 'IMPORTANT' callout, and 'USE CASES' section repeat earlier points), but the front-loaded ordering and scannable bullets keep it effective.

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?

The tool has no output schema, so the description compensates by documenting the exact response array shape, per-image success/failure fields, and error handling. It also covers prerequisites, downstream dependencies, and batch behavior, leaving an agent with enough information to call it correctly.

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?

The schema already documents both parameters at 100% coverage, so the description doesn't need to compensate; however, it adds beyond the schema by specifying supported formats (PNG/JPG/GIF/WebP), URL accessibility, and the underscore substitution behavior for filenames. The optional `names` parameter is not mentioned in the description, but its schema entry already contains detailed usage guidance.

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: 'Upload images directly to Metadata platform library to create image creatives.' It names the downstream sibling create_update_image_ad and frames generate_brand_creative as a preceding step, which makes the tool's role in the ad workflow unambiguous.

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?

It explicitly declares 'REQUIRED STEP IN AD CREATION WORKFLOW' and states it 'MUST be called between generate_brand_creative and create_update_image_ad.' It also lists distinct use cases (existing images, generated images, batch uploads), giving the agent concrete conditions for invoking it.

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