Skip to main content
Glama

ADS Beast

prepare_negative_keywords_add

Prepare negative keywords for a client's Google Ads account: a shared list attached to the named campaigns, or to every enabled Search, Shopping and Display campaign. If it cannot be attached anywhere, nothing is left behind. Changes nothing: stores a preview_id (15 min, single use) to show, then execute_prepared_change.

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": {
      "client_id": "<client_id>",
      "keywords": "<keywords>",
      "reason": "<reason>"
    },
    "name": "prepare_negative_keywords_add"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy, with numbers (shown to the approver).
keywordsYesNegative keywords to add, one phrase per item, at most 50 (the executor's cap).
client_idYes
list_nameNoName of the shared negative list; a dated name is used by default.
campaign_idsNoADS Beast ids of the Google campaigns to attach the list to; omit for every enabled Search, Shopping and Display campaign.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, which alone would not explain what the write actually is; the description fills that gap by stating that nothing in the ad account changes, that a preview_id is stored for 15 minutes and is single-use, and that a failed attachment leaves nothing behind. This is precisely the kind of side-effect, expiry, and atomicity information the annotations cannot convey.

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?

Two dense sentences, front-loaded with what is produced and followed by the no-side-effects/expiry contract. Nothing is padded, though the clause "If it cannot be attached anywhere, nothing is left behind" is telegraphic enough that it takes a second read.

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?

For a five-parameter mutation-preparation tool with no output schema, the definition covers the essential points: what gets created, default targeting scope, the preview token lifetime and usage, and the handoff to the executor. It stops short of describing what the preview shows or how attachment failures are surfaced, which an agent might want before calling.

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?

With 80% schema coverage the schema already documents keywords, reason, list_name and campaign_ids, so the baseline is 3. The description goes beyond it by making the semantics of campaign_ids explicit (omit = every enabled Search, Shopping and Display campaign) and by framing the output as a shared list, which clarifies role rather than restating types.

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?

"Prepare negative keywords for a client's Google Ads account" is a specific verb+resource, and the sentence continues to define the exact form of the result: a shared list attached either to the named campaigns or to every enabled Search, Shopping and Display campaign. An agent can distinguish this from the executor and from unrelated prepare_* tools without opening the schema.

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?

The description routes the agent through the intended two-step flow by naming execute_prepared_change as the follow-up, and it states the fallback scope (all enabled Search/Shopping/Display campaigns) when campaign_ids is omitted. It does not state when to avoid this tool or how it compares to other prepare_* tools, so it is clear context without explicit exclusions.

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.