Skip to main content
Glama

Google Ads: cap how often one person sees the ads

ads_set_frequency_cap
DestructiveIdempotent

Cap how often one person sees a Google Ads campaign's ads: at most N impressions per person per day, week or month. Demand Gen, Display and Video campaigns only (Search ads show only when someone searches, and Performance Max manages its own). Call without confirm first: Google checks the change and nothing changes; show the person the before and after. remove: true takes the cap off.

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>",
      "campaign_id": "<campaign_id>"
    },
    "name": "ads_set_frequency_cap"
  }
}

Input Schema

NameRequiredDescriptionDefault
removeNoTake the campaign's cap off (Google decides again)
confirmNoLeave false to preview: nothing changes and the preview shows exactly what would happen. Set true only after the user has agreed to this exact change.
campaign_idYes
customer_idYes
frequency_capNoe.g. {impressions: 3, per: 'week'}

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing a preview-by-default flow (nothing changes until confirm is true) and what remove:true does. The destructiveHint=true is thus contextualized. It stops short of stating what happens to an existing cap when a new frequency_cap is supplied, or any permission/scope requirements.

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-loads the core action, then type restrictions, then the preview/confirm workflow, then the remove flag. Dense and mostly waste-free, though the parenthetical explanation of Search/Performance Max is slightly wordy.

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 mutation tool with a nested object and no output schema, the description covers the preconditions, the safe call sequence, and the removal path, which is what an agent needs to invoke it correctly. Remaining gaps (return payload, identifier sourcing) are minor.

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 60%, and the description compensates by explaining the three behavioral parameters: confirm as preview gate, remove as cap removal, and frequency_cap as impressions per person per period. It does not clarify customer_id/campaign_id semantics, but those are conventional identifiers.

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 precise verb and resource: cap impression frequency for a Google Ads campaign's ads, at N impressions per person per day/week/month. It also names the campaign types it applies to, so an agent can tell it apart from budget, status, or bidding siblings.

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?

Explicitly bounds applicability (Demand Gen, Display and Video only) and explains why Search and Performance Max are excluded. It additionally prescribes the call sequence: call without confirm first, then set confirm true only after user agreement.

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.