google-ads-write-mcp

Overview Schema Source Related Servers Discussions Admin

add_negative_keywords

Add negative keywords to a campaign or ad group to block unwanted searches, preventing ads from showing for irrelevant queries. Supports phrase, exact, or broad match with dry-run by default.

Instructions

Add NEGATIVE keywords at campaign level (campaign_id) or ad-group level (ad_group_id). match_type: PHRASE (default) | EXACT | BROAD. Dry run unless confirm=true.

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": {
      "customer_id": "<customer_id>",
      "keywords": "<keywords>"
    },
    "name": "add_negative_keywords"
  }
}

Input Schema

Name	Required	Default
`confirm`	No
`keywords`	Yes
`match_type`	No	PHRASE
`ad_group_id`	No
`campaign_id`	No
`customer_id`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.8.0Aug 30, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the behavioral burden and does disclose the most important trait: 'Dry run unless confirm=true.' It also reveals the default match type. It does not cover permissions, idempotency, or error conditions, but it gives the safety-critical behavior upfront.

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?

Two compact sentences with no filler. The purpose and placement are first, then match type, then the critical dry-run behavior; every clause earns its place.

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?

The description is mostly complete for a moderately complex tool: it identifies placement, match type, and default dry-run mode. The main gap is that it never explicitly states that one of campaign_id/ad_group_id should be supplied or what happens if both/neither are set, though 'or' implies the intended exclusivity.

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 0%, but the description compensates by explaining match_type values/default, tying campaign_id and ad_group_id to placement levels, and defining confirm's dry-run semantics. customer_id and the exact format/syntax of keywords are not described, but the main disambiguating parameter details are present.

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 states a specific action ('Add NEGATIVE keywords') on a defined resource with placement levels (campaign_id / ad_group_id). The capitalized 'NEGATIVE' distinguishes it from the sibling add_keywords tool.

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 clearly scopes when to use this tool: adding negative keywords at campaign or ad-group level, with match-type control and dry-run by default. It does not explicitly call out alternatives or exclusions, but the negative-keyword framing and sibling list make the choice clear.

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