AdCopilot

Google Ads: add account-level negative keywords

add_account_negatives

Adds account-level negative keywords: words blocked in every campaign.

Use for words the business never wants to show for anywhere (e.g.
brand-safety terms, "free", "jobs"). In the Google Ads API these live in
the account's single account-level negative keyword list (a shared set
of type ACCOUNT_LEVEL_NEGATIVE_KEYWORDS, linked to the account by a
CustomerNegativeCriterion). This tool adds the words to that list if the
account already has one, and otherwise creates the list, adds the words
and links it to the account. remove_account_negatives takes words back
out.

Limits (Google's): an account has at most one account-level list, of up
to 1,000 keywords. Google applies it to the search and shopping
inventory of Search, Shopping, Performance Max, App, Smart and Local
campaigns — not to Display or Video placements.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    keywords: List of keyword objects, each with:
        - text: The keyword text (e.g., "free").
        - match_type: One of: EXACT, PHRASE, BROAD. Default: BROAD.
        Exact duplicates are dropped.

Returns:
    Dictionary with the account-level list's shared_set_id, whether it
    was created now, and the keywords added.

Tools revision: 5c9bea8f.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`keywords`	Yes
`customer_id`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the annotations, it discloses the create-if-missing behavior ('adds the words to that list if the account already has one, and otherwise creates the list'), Google's one-list/1,000-keyword caps, duplicate dropping, and which campaign types the list applies to vs. which it doesn't. That is substantive operational context an agent could not infer from readOnlyHint/destructiveHint alone.

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 structure is excellent — purpose, when-to-use, API mechanics, limits, args, returns — and it is front-loaded. It is on the long side, with some Google Ads internals (CustomerNegativeCriterion, shared set type) that a calling agent does not strictly need, though they do support the behavior claims.

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?

For a two-parameter mutation with no schema descriptions, the definition covers everything: preconditions, side effects, hard limits, default match type, and a described return payload (shared_set_id, created flag, keywords added). Combined with the existing output schema, an agent has sufficient information to invoke it 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?

Schema description coverage is 0%, so the description must carry the parameter burden, and it does: customer_id is documented as digits only with no hyphens, and keywords is documented down to the nested text and match_type fields, the EXACT/PHRASE/BROAD enum, the BROAD default, and duplicate suppression. Nothing in the args is left undefined.

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 names a specific verb and resource ('adds account-level negative keywords') and immediately defines the scope as 'words blocked in every campaign,' which separates it from campaign-, ad-group-, and shared-list-level siblings. The explicit contrast with remove_account_negatives and the account-level list framing leave no ambiguity about what this tool does.

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?

It states exactly when to use it ('words the business never wants to show for anywhere') with concrete examples like brand-safety terms, 'free', and 'jobs'. It names the inverse tool (remove_account_negatives) and, through the account-level scoping, implicitly rules out the per-campaign and per-ad-group negative keyword tools.

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

All AdCopilot 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?