Skip to main content
Glama

Metadata MCP Connector

Delete Negative Keyword Lists

delete_negative_keyword_lists
Destructive

Permanently delete one or more entire Google Ads negative keyword lists, only when the user has explicitly asked.

            PURPOSE:
            Wipe negative keyword lists that the user has named for deletion. The platform
            supports a multi-id delete in one HTTP call, so batch every list the user
            identified into a single tool call instead of calling once per list.

            ONLY CALL THIS TOOL WHEN THE USER HAS EXPLICITLY NAMED LISTS TO DELETE.
            Examples that qualify:
            - "Delete the 'Old competitors' list"
            - "Drop these three lists: A, B, C"
            - "Yes, delete the one I just showed you"
            Examples that do NOT qualify:
            - "Create a new list called X" — even if the 20-list account cap blocks the
              create call, do NOT pick a list and delete it. Surface the cap to the user
              (via list_negative_keywords_list so they see what's there), and ask which
              list(s) THEY want to delete before calling this tool.
            - "Clean up my lists" — too vague; first list_negative_keywords_list, present
              the current set, and let the user pick which to drop.

            WARNING:
            This deletes the LIST itself (every keyword in it goes with it, and any
            campaigns attaching the list lose the attachment). To remove specific
            keywords inside a list without dropping the list, use
            remove_keywords_from_negative_list instead.

            LOOKING UP LIST IDS:
            Call list_negative_keywords_list to map the names the user gave you to ids.
            The 'id' field returned there is what you pass here.

            COMMON USE CASES:
            1. Delete a single list the user named:
               delete_negative_keyword_lists(listIds=[43256533])

            2. Delete several at once (mirrors the UI's "Select rows -> Delete" action):
               delete_negative_keyword_lists(listIds=[43256533, 43258891, 43261107])

            PARAMETERS:
            - listIds (array of integers, required, min 1): IDs of the negative keyword
              lists the user asked to delete, as returned by list_negative_keywords_list.

            RESPONSE FORMAT:
            Returns the platform response. The channels service typically responds with
            204 No Content on success, in which case the wrapper returns a code 204 +
            Success envelope with the ids that were deleted.

            CHANNEL SCOPE:
            BOTH search channels are supported: pass channel=MICROSOFT_ADS for Microsoft
            Ads (Bing) and channel=GOOGLE_ADS for Google. The two channels hold SEPARATE
            lists, so never substitute one channel for the other to get "close enough"
            results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
channelNoAd channel scope. Both search channels are supported. These are PER-CHANNEL resources: GOOGLE_ADS and MICROSOFT_ADS hold separate sets, and one is invisible to the other. Defaults to GOOGLE_ADS when the user does not say which.GOOGLE_ADS
listIdsYesIDs of the negative keyword lists to delete (from list_negative_keywords_list).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, the description discloses the full destructive cascade: deleting the list removes every keyword in it and detaches any campaigns using it. It also warns that deletion is permanent and explains the response envelope on success, which is essential because there is no output schema.

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 description is long but well-structured with clear headings, a front-loaded warning, and each section serving a purpose. Some redundancy exists in the qualification examples, but for a destructive tool with nuanced guardrails, the detail is justified.

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?

Given no output schema, the description covers the response format, side effects, prerequisites, batching behavior, and channel scope. An agent has enough information to call the tool correctly and avoid irreversible mistakes.

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 100%, so baseline is 3. The description adds value by explaining how to obtain listIds via list_negative_keywords_list and providing concrete use cases, though the channel parameter is already fully documented in the schema.

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 opens with a specific action and resource: 'Permanently delete one or more entire Google Ads negative keyword lists.' It explicitly differentiates from remove_keywords_from_negative_list and create_negative_keywords_list, so an agent can distinguish it from siblings without inspecting schemas.

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 gives explicit when-to-call guidance ('ONLY CALL THIS TOOL WHEN THE USER HAS EXPLICITLY NAMED LISTS TO DELETE'), provides qualifying and non-qualifying examples, names the prerequisite lookup tool, and directs to remove_keywords_from_negative_list for partial removal. It also warns against cross-channel substitution.

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