Metadata MCP Connector

Create Microsoft Ads Image Extension (BETA)

create_microsoft_image_extension

Attach visual imagery (1-20 product / lifestyle shots) to a Microsoft Ads (Bing) text ad to lift click-through. BETA. Re-uses assets already uploaded to the Metadata image library — pass their IDs, not raw files.

            ALSO KNOWN AS: image extension, image asset, ad image, visual extension, picture extension, photo extension, hero image

            KEYWORDS: image, image extension, photo, picture, visual, hero, asset, library, BETA, microsoft ads, bing, extension, CTR

            WHEN TO USE:
            - "Attach images to our Microsoft Ads text ad"
            - "Add image library IDs 123 and 456 as a Bing image extension"
            - "Create a Microsoft Ads image extension showing product photos under our search ads"

            WHEN NOT TO USE:
            - The image is a logo / brand mark → use create_microsoft_business_logo_extension
            - You haven't uploaded the assets yet — image extensions reference library IDs, so upload to the image library first.
            - Want to drive clicks via text snippets → use create_microsoft_sitelink_extension / callout
            - Same images for Google Ads → use create_google_image_extension

            INPUTS:
            - image_library_ids (required): 1-20 IDs from the Metadata image library.
            - alternative_text:  accessibility alt text (≤90 chars).
            - display_text:      short caption overlaid on the image (≤35 chars). E.g. "Shop Now".
            - destination_url:   landing page when the image is clicked.

            EXAMPLE:
            create_microsoft_image_extension(
                image_library_ids=[123, 456],
                alternative_text="Product hero shot",
                display_text="Shop Now",
                destination_url="https://example.com/landing",
            )

Input Schema

TableJSON Schema

Name	Required	Description
`display_text`	No
`destination_url`	No
`alternative_text`	No
`image_library_ids`	Yes	1-20 image-library IDs.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The description adds useful behavior beyond annotations: it is BETA, reuses already-uploaded Metadata library assets rather than accepting raw files, and attaches imagery to a text ad. It does not contradict readOnlyHint=false or destructiveHint=false, though it leaves the target-ad selection implicit.

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?

Purpose and BETA warning are front-loaded, sections are clearly organized, and the example earns its place. Some redundancy in the ALIASES and KEYWORDS lists and repeated WHEN TO USE phrasings keeps it from being maximally concise.

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?

Input semantics, prerequisites, and routing are well covered, but the description never states how the target Microsoft Ads text ad is selected. The input schema has no ad/campaign ID, so an agent must infer that the active/current ad or account context is used, which is a meaningful gap for an attach/create tool.

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

Parameters5/5

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

Schema coverage is only 25%, but the description compensates by explaining every parameter: image IDs from the Metadata library, alt-text accessibility with ≤90 chars, display-text overlay with ≤35 chars, and destination URL as the landing page. A concrete example further clarifies usage.

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/resource: it creates/attaches a Microsoft Ads image extension to a Bing text ad, using 1-20 library images. The WHEN NOT TO USE section also disambiguates it from logo, sitelink, callout, and Google-image siblings.

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?

Explicitly lists WHEN TO USE triggers and WHEN NOT TO USE exclusions with named alternatives: logos → create_microsoft_business_logo_extension, text snippets → sitelink/callout, Google Ads → create_google_image_extension, and missing uploads → upload to the image library first.

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

All Metadata MCP Connector 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?