Metadata MCP Connector

Get Ad Details

get_ad_details

Read-only

Get complete details and configuration for one or more ads from the Metadata platform.

                USAGE INSTRUCTIONS FOR LLM:
                Use this tool when users want to:
                - Get complete ad details by ad ID
                - Retrieve ad configuration including content, targeting, and creative assets
                - Check existing ad settings before making modifications
                - Analyze ad performance data and configuration
                - Get creative library information associated with ads
                - Extract ad content like text, headline, CTA, links for reference
                - the value returned libraryCreative labelName corresponds to the library/image name.

                WHEN TO USE:
                - User asks "show me ad details for ID X"
                - User wants to see ad configuration: "what's in ad 182124?"
                - User needs ad content: "get the text/headline/CTA from ad Y"
                - User wants to check ad settings before editing
                - User asks "what creative is used in ad Z?"
                - User needs to analyze existing ad setup

                INPUT PARAMETERS:
                - ids: Flexible format for specifying ad IDs:
                    * Single integer: 182124
                    * Comma-separated string: "182124,182123,182125"

                EXAMPLE CALLS:
                - get_ad_details(ids=182124) (single)
                - get_ad_details(ids="182124,182123,182125") (multiple)

                DETAILED RESPONSE INCLUDES:
                AD CONFIGURATION:
                - Basic info: id, name, channelType (FACEBOOK/LINKEDIN), adType (IMAGE/VIDEO/etc.)
                - Status: completionStatus, aiState, renameAllowed

                AD CONTENT:
                - text: Main ad copy/body text
                - headline: Ad headline text
                - link: Landing page URL
                - description: Additional ad description
                - ctaType: Call-to-action button (e.g., "Get_Demo", "Learn_More")

                CREATIVE ASSET DETAILS:
                - libraryId: Creative asset ID reference
                - libraryCreative object with:
                    - id, labelName (filename)
                    - url: Full-size creative asset URL
                    - thumbnail: Thumbnail URL
                    - dimensions: width, height in pixels
                    - sizeInKb: File size
                    - content_type: image/png, image/jpeg, etc.
                    - created_date: When creative was uploaded

                METADATA:
                - tags: Ad tags/labels
                - created/modified dates
                - AI processing state

                ERROR HANDLING:
                - If ad ID doesn't exist, API returns empty array
                - Always validate that IDs are integers before making request
                - Handle both single ID and multiple ID requests

                EXAMPLE USAGE:
                - get_ad_details(ids=182124) - Single ad by integer
                - get_ad_details(ids="182124,182123,182125") - Multiple ads by comma-separated string

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ids`	Yes	Ad ID(s) to get details for. Can be: single integer (182124) or comma-separated string ('182124,182123').

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The description adds meaningful behavioral context beyond the readOnly/non-destructive annotations: it explains that non-existent IDs return an empty array, advises validating integer IDs, and clarifies that libraryCreative labelName corresponds to the filename. This is useful operational disclosure, though it omits rate-limit or pagination details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and well-sectioned, but it is overlong and repetitive: 'USAGE INSTRUCTIONS' and 'WHEN TO USE' overlap heavily, and 'EXAMPLE CALLS' duplicates 'EXAMPLE USAGE' with identical examples. It would be stronger if these redundant sections were merged.

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?

With no output schema, the description compensates by thoroughly detailing the response structure: ad configuration, content fields, creative asset details, metadata, and error handling. For a one-parameter read-only tool, an agent has enough context to invoke it and interpret results confidently.

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 fully documents ids, so the baseline is 3. The description adds value through call syntax examples and the explicit instruction to validate IDs as integers, plus handling of both single and comma-separated multiple IDs.

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 immediately states 'Get complete details and configuration for one or more ads from the Metadata platform,' specifying a clear verb and resource. It also enumerates concrete use cases like retrieving configuration, content, creative assets, and pre-edit checks, making it distinguishable from sibling tools.

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?

A dedicated 'WHEN TO USE' section gives concrete user phrasings and intents, so an agent knows when to invoke this tool. However, it never names alternatives like search_ads_by_names or fetch_creative_details and provides no explicit when-not-to-use guidance.

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?