Google Ads - AdLoop

Overview Schema Source Related Servers Discussions Admin

Draft a campaign

draft_campaign

Prepares a Google Ads campaign structure preview with budget, paused campaign, ad group, keywords, and geo/language targeting, returning a plan for later confirmation. Ads are not created.

Instructions

Draft a full campaign structure — returns a PREVIEW, does NOT create anything.

Creates: CampaignBudget + Campaign (PAUSED) + AdGroup + optional Keywords

geo targeting + language targeting. Ads are NOT included — use draft_responsive_search_ad after the campaign exists.

bidding_strategy: MAXIMIZE_CONVERSIONS | TARGET_CPA | TARGET_ROAS | MAXIMIZE_CONVERSION_VALUE | TARGET_SPEND | MANUAL_CPC target_cpa: required if bidding_strategy is TARGET_CPA (in account currency) target_roas: required if bidding_strategy is TARGET_ROAS keywords: list of {"text": "keyword", "match_type": "EXACT|PHRASE|BROAD"} search_partners_enabled: include ads on Search partners display_network_enabled: enable Search campaign display expansion display_expansion_enabled: alias for display_network_enabled max_cpc: manual CPC bid for the initial ad group when bidding_strategy is MANUAL_CPC, or the Maximize Clicks CPC cap when bidding_strategy is TARGET_SPEND geo_target_ids: REQUIRED list of geo target constant IDs Common: "2276" Germany, "2040" Austria, "2756" Switzerland, "2840" USA, "2826" UK, "2250" France. Full list: Google Ads API geo target constants. language_ids: REQUIRED list of language constant IDs Common: "1001" German, "1000" English, "1002" French, "1004" Spanish, "1014" Portuguese. Full list: Google Ads API language constants.

Call confirm_and_apply with the returned plan_id to execute.

Input Schema

TableJSON Schema

Name	Required	Default
`max_cpc`	No
`keywords`	No
`target_cpa`	No
`customer_id`	No
`target_roas`	No
`channel_type`	No	SEARCH
`daily_budget`	Yes
`language_ids`	Yes
`ad_group_name`	No
`campaign_name`	Yes
`geo_target_ids`	Yes
`bidding_strategy`	Yes
`display_network_enabled`	No
`search_partners_enabled`	No
`display_expansion_enabled`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.13.2Sep 7, 2026
Removedv0.13.0Jul 22, 2026
First observedv0.9.0Jun 19, 2026

TDQS

A4.1/5.0

Behavior1/5

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

The description states 'returns a PREVIEW, does NOT create anything' and instructs to call confirm_and_apply to execute, which contradicts the annotation readOnlyHint=false. This annotation implies the tool may modify data, creating a direct conflict with the description's claim of no actual creation.

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 logically structured with bullet points and covers all key aspects, but it is somewhat verbose with repeated parameter explanations. It could be tightened slightly without losing clarity.

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 description provides all necessary context: what the tool does, what it does not do, parameter details including required fields and examples, and the next step (confirm_and_apply). It is sufficiently comprehensive for an agent to use correctly.

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?

The description adds significant meaning to the parameters, explaining bidding_strategy options, target_cpa/roas requirements, max_cpc behavior, and providing common geo and language ID examples. This goes well beyond the schema's bare types and defaults.

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 clearly states it drafts a full campaign structure and returns a preview, explicitly listing what is created in the preview and what is excluded (ads). It distinguishes itself from other drafting tools like draft_responsive_search_ad.

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?

The description explains when to use the tool (to draft a campaign) and when to use a follow-up tool (draft_responsive_search_ad after the campaign exists). It also directs the user to confirm_and_apply to execute the preview, providing a clear workflow.

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

Deploy Server