AdCopilot

Google Ads: add to negative keyword list

add_to_negative_keyword_list

Adds negative keywords to an existing shared negative keyword list.

Every campaign the list is attached to picks the new words up at once.
remove_from_negative_keyword_list takes words back out. Find existing
lists with the search tool, e.g.
SELECT shared_set.id, shared_set.name, shared_set.member_count
FROM shared_set WHERE shared_set.type = 'NEGATIVE_KEYWORDS'
AND shared_set.status = 'ENABLED'.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    shared_set_id: The ID of the negative keyword list.
    keywords: List of keyword objects, each with:
        - text: The keyword text (e.g., "jobs").
        - match_type: One of: EXACT, PHRASE, BROAD. Default: BROAD.
        Exact duplicates are dropped; large lists are sent in batches.

Returns:
    Dictionary with the created keyword resource names and count.

Tools revision: 5c9bea8f.

Input Schema

TableJSON Schema

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

Annotations cover the safety profile (not read-only, not destructive, not idempotent, closed-world), and the description adds behavior they don't: changes propagate to every attached campaign immediately, exact duplicates are silently dropped, and large input lists are batched. The immediate-propagation warning is exactly the kind of side effect an agent needs before writing.

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?

Front-loaded with the one-line purpose and the propagation warning, then cleanly split into Args and Returns. The embedded multi-line SQL block is useful but heavy relative to the rest, and the trailing 'Tools revision' tag is noise rather than content.

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?

An output schema exists, yet the description still telegraphs the return (resource names and count), so the caller knows what to report back. Combined with dedup, batching, and default match type, nothing material is missing for a three-param write tool.

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 coverage is 0% and the item schema is a bare additionalProperties:string object, so the description carries the full burden — and does: customer_id is numbers only with no hyphens, shared_set_id identifies the list, and each keyword object needs text plus a match_type restricted to EXACT/PHRASE/BROAD with BROAD as default. This documents constraints the schema cannot.

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 and resource: adds negative keywords to an *existing shared* negative keyword list. That scope word 'existing' implicitly separates it from create_negative_keyword_list, and the explicit pointer to remove_from_negative_keyword_list separates it from the removal sibling.

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?

Gives the operative context (the list must already exist and be attached to campaigns), names the inverse tool, and supplies a concrete SQL query against the search tool to locate shared_set_id when the caller doesn't have one. That is actionable routing guidance rather than inference.

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?