Skip to main content
Glama

Create Google Search / Performance Max Campaign

google_ads_create_search_campaign

Create a paused Google Search campaign (responsive search ad, phrase-match keywords) in the customer's own Google Ads account, saved as a draft the customer activates on the Ads page. Search only; needs the ads add-on and a connected account.

Input Schema

NameRequiredDescriptionDefault
nameYesCampaign name
statusNoPAUSED
finalUrlYesDestination landing page URL
keywordsNoTarget keywords and match types
languageNoAd language as a Google language code (sv, en, de, …); defaults to the posting language
headlinesYesRSA Headlines (3-15, max 30 chars each)
geoTargetsNoISO 3166-1 alpha-2 country code(s), e.g. ["SE"]; the first supported one is used
targetRoasNoTarget ROAS multiplier (e.g. 3.5 for 350%)
adGroupNameNo
descriptionsYesRSA Descriptions (2-4, max 90 chars each)
targetCpaCentsNoTarget CPA in cents if using Target CPA bidding
dailyBudgetCentsYesDaily budget in minor units of the ad account currency (e.g. 2000 = 20.00)
advertisingChannelTypeNoSEARCH

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the campaign is created PAUSED as a draft, requires manual activation on the Ads page, and depends on the ads add-on plus a connected account. These are real behavioral facts beyond the schema; it omits only edge cases and error behavior.

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?

A single sentence plus one compact caveat clause, front-loaded with the core action and no wasted words. Everything an agent needs at a glance is in the first half.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter mutation tool with no annotations and no output schema, the description covers the essentials: what is created, its state, prerequisites, and that the customer activates it. Return values are unspecified, but the omission is minor for a creation tool.

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 77%, so most parameters are already documented. The description adds little per-parameter meaning and slightly misaligns with the schema: it says 'phrase-match keywords' and 'Search only', while the schema exposes EXACT/PHRASE/BROAD match types and a PERFORMANCE_MAX/DISPLAY advertisingChannelType enum.

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?

Specific verb+resource: it creates a paused Search campaign with an RSA and phrase-match keywords, which cleanly separates it from google_ads_manage_campaign and list_ad_campaigns. The title says 'Search / Performance Max' while the description says 'Search only', a minor internal inconsistency that slightly muddies scope.

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?

Gives clear preconditions: needs the Google Ads add-on and a connected account, and it writes to the customer's own account as a draft they later activate. It does not explicitly name sibling alternatives (e.g. manage_campaign for edits), but the context is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources