Loop Marketing

Create launch draft

create_launch_draft

Prepare a new campaign as a proposal in the Loop inbox (needs a propose key). Same checks as the Loop form: connected channel, unique name, budget plan, guardrails. Nothing is sent to the ad platform; a person approves it in Loop.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "channel": "<channel>",
      "amount": "<amount>",
      "endTime": "<endTime>"
    },
    "name": "create_launch_draft"
  }
}

Input Schema

Name	Required	Description
`link`	No	Destination URL (store or website).
`name`	Yes	Campaign name. Must not exist in the workspace or wait in the inbox already.
`amount`	Yes	Total budget in major units of the currency the channel's ad account bills in (e.g. 30000 for ¥30,000). Channels whose account currency cannot be read use the workspace currency.
`channel`	Yes	Ad platform key, e.g. meta, google_ads, tiktok, apple_search_ads, microsoft_ads, linkedin_ads, amazon_ads. Must be connected.
`draftId`	No	Id of a pending draft to replace. Omit for a new draft.
`endTime`	Yes	End, ISO 8601 with offset, e.g. 2026-11-30T23:59:59+09:00.
`appEvent`	No	Meta app event to optimise for instead of installs (see list_app_events).
`bodyText`	No
`headline`	No
`countries`	No	ISO country codes, e.g. ["JP"].
`startTime`	No	Optional start, ISO 8601 with offset.
`placements`	No	Meta placements. Omit to let Meta choose.
`moreHeadlines`	No	Google Ads App campaigns only: the 2nd to 5th headlines (Google needs 2–5, each up to 30 wide; full-width counts as 2).
`amountCurrency`	No	The currency you mean the amount in (ISO 4217, e.g. JPY). If the ad account bills in another currency, nothing is saved.
`libraryAssetId`	No	Library file id from this workspace.
`imageCreativeId`	No	Creative id from this workspace.
`youtubeVideoIds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description adds genuinely useful behavior: an auth requirement (propose key), the fact that nothing reaches the ad platform, and that a human approves the proposal in Loop. It also lists the validation gates (connected channel, unique name, budget plan, guardrails). It stops short of describing failure behavior or how a rejected proposal surfaces.

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

Conciseness5/5

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

Three tight sentences: purpose and destination first, then required checks, then the critical reassurance about non-delivery and approval. No sentence is filler, and the most decision-relevant fact (nothing is sent to the ad platform) is given its own clause.

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?

With 17 parameters, no output schema, and only coarse annotations, the description could reasonably say more, e.g. what identifier a successful draft returns, or how channel choice constrains which creative parameters are relevant. It covers the concept, prerequisites, and approval flow adequately, but leaves the mutation's result and failure modes implicit.

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 coverage is 82%, so the schema already documents most parameters thoroughly, including currency semantics and ISO timestamps. The description largely restates those constraints ('connected channel, unique name') rather than adding new meaning, and it says nothing about the seven-plus creative, placement, and country parameters that only the schema explains. Baseline 3 is appropriate.

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 names a specific verb and resource: prepare a new campaign as a proposal in the Loop inbox. It also makes the outcome explicit (a pending proposal, not a live campaign), which separates it from read-side siblings such as list_proposals and get_campaign. It does not, however, explain how this differs from the close sibling prepare_campaign_change, so an agent must infer the boundary.

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?

It states a clear use case and a prerequisite ('needs a propose key'), and notes the same validation checks as the Loop form apply. What is missing is explicit routing guidance: no statement of when to prefer prepare_campaign_change or how to handle an existing pending draft beyond the draftId parameter.

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

All Loop Marketing 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?