Google Ads MCP Server

Set Conversion Action Primary

set_conversion_action_primary

Destructive

Marks a conversion action as primary for Smart Bidding optimization or secondary for reporting only. Use to make campaigns optimize toward real outcomes like phone calls instead of soft actions.

Instructions

Marks a conversion action as primary (optimized toward by Smart Bidding) or secondary (observed/reported only).

This is the main lever for making campaigns optimize toward real outcomes (e.g. phone calls) instead of soft actions (page views, direction clicks). Find ids with list_conversion_actions.

Note: some system-generated conversion actions cannot be edited via the API; the error will say so if this one can't.

Input Schema

TableJSON Schema

Name	Required	Description
`primary`	Yes	True to make it primary, False to demote to secondary.
`customer_id`	Yes	The Google Ads account.
`validate_only`	No	If True, only validates the request.
`conversion_action_id`	Yes	The numeric id of the conversion action.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.2Oct 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only provide destructiveHint=true, which is somewhat counterintuitive for a setting toggle but acknowledges mutability. The description adds valuable context about what primary vs secondary means, the error behavior for system-generated actions, and the optimization implications. It doesn't cover reversibility or exact API error formats, but provides solid beyond-annotation detail.

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?

Efficiently front-loads the core action in the first sentence, then explains the semantic impact, provides a discovery hint, and notes an edge case—all in three concise sentences with zero waste.

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?

Given a boolean mutation tool with full schema coverage and an output schema, the description is nearly complete. It covers purpose, side effects, discovery, and a known limitation. A bit more on idempotency or required permissions could push it to 5, but it's strong.

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 description coverage is 100%, so parameters are fully documented in the schema. The description adds no parameter-specific syntax or format details beyond what's in the schema, though it does clarify the primary parameter's meaning in context. Baseline 3 is appropriate.

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 (sets/marks) and resource (conversion action primary/secondary), and explains the domain meaning (Smart Bidding optimization target). Clearly distinguishable from siblings like list_conversion_actions or set_campaign_conversion_goals.

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?

Provides clear context for why you'd use it (optimizing toward real outcomes vs soft actions) and points to list_conversion_actions for finding IDs. However, it doesn't explicitly state when NOT to use it or name direct alternatives for setting conversion goals.

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