Versium REACH

Export List To Ads Mcp Tool

export_list_to_ads

Destructive

Start an Ad Platform Export: push a list's Online Audience to the user's connected ad account as an Ad Platform Audience. Not billed.

Find the platform, `account_id` and, to add to an existing Ad Platform Audience, its `audience_id` with `ads_export_options`. Pass `audience_name` to create a new Ad Platform Audience instead. The export runs in the background; check it with `ads_export_status` and the returned `history_id`.

Only one export of a list to a platform runs at a time. When one is already running, no new export starts: `already_in_progress` is true and the response describes the running export, whose account and audience may differ from this request.

Input Schema

Name	Required	Description
`list_id`	Yes
`platform`	Yes
`account_id`	Yes	Ad account ID from `ads_export_options`
`audience_id`	No	Existing Ad Platform Audience to add the list to, from `ads_export_options`. Pass this or audience_name, not both.
`audience_name`	No	Name for a new Ad Platform Audience. Pass this or audience_id, not both.

Output Schema

Name	Required	Description
`status`	No
`list_id`	No
`message`	No
`platform`	No
`account_id`	No	The export's target ad account
`history_id`	No	Pass to `ads_export_status`
`audience_id`	No	The existing Ad Platform Audience the export adds to
`audience_name`	No	The name of the Ad Platform Audience the export creates
`already_in_progress`	No	True when no new export started because one was already running; the other fields then describe that export

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Adds substantial context beyond annotations: 'Not billed', background/async execution, and the single-concurrent-export rule with the already_in_progress response including the possibility that the running export's account/audience differ from the request. These are non-obvious behavioral traits that annotations (destructive/not-idempotent) do not 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?

Front-loads the core action, then prerequisites, then the async/concurrency caveat. Well organized and largely waste-free, though the three-paragraph split is slightly longer than strictly necessary.

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?

For a destructive, non-idempotent mutation tool with an output schema already covering returns, the description still supplies everything an agent needs: prerequisites, async follow-up via history_id, and the concurrency edge case. Complete against the available structured data.

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?

Schema coverage is 60%; the description compensates by explaining where account_id/audience_id come from (ads_export_options) and the mutually exclusive audience_id vs audience_name semantics. list_id and platform rely on the enum and general context, but the description's mapping of audience_name to 'create new' adds real meaning beyond the schema.

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 (start/push) and resource (Ad Platform Export / Online Audience to ad account), and clearly distinguishes itself from siblings ads_export_options, ads_export_status, and the append tools. An agent can identify the exact action without opening the schema.

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 says how to find platform/account_id/audience_id via ads_export_options, when to use audience_name vs audience_id (create new vs add existing, not both), and to check progress with ads_export_status. Also documents the concurrent-export exclusion. Nothing left to inference.

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

All Versium REACH 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?