Skip to main content
Glama

Activate or pause an ad

ads_set_status
Destructive

Set a campaign, ad set (TikTok ad group, LinkedIn campaign) or ad to ACTIVE or PAUSED. TikTok and LinkedIn need level. Activating a LinkedIn draft campaign group from ads_create_linkedin_campaign also activates its campaign and ad. ACTIVE starts spending real money on the ad account: never activate without the user's explicit confirmation of the budget and dates. Setting the status an object already has is a no-op; one object's status can change four times an hour, so do not toggle it on and off. Meta changes are paced and limited so the ad account does not look automated: on ads_change_limited, wait retryAfterSeconds before retrying.

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": {
      "adAccountId": "<adAccountId>",
      "objectId": "<objectId>",
      "status": "<status>"
    },
    "name": "ads_set_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelNo
statusYes
objectIdYes
platformNometa_ads, tiktok_ads or linkedin_ads. Needed only when the profile has more than one ad network and no accountId is given.
accountIdNoThe Facebook accountId from list_accounts. Without it, pass profileId to use that profile's Facebook connection.
profileIdNoA profileId from list_profiles. Optional when accountId is given, which names its profile; if both are given they must agree.
adAccountIdYes
campaignRecordIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / platform / description
      Previous value: -"meta_ads or tiktok_ads. Needed only when the profile has both ad networks and no accountId is given."New value: +"meta_ads, tiktok_ads or linkedin_ads. Needed only when the profile has more than one ad network and no accountId is given."
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "meta_ads",
      -  "tiktok_ads"
      -]New value: +[
      +  "meta_ads",
      +  "tiktok_ads",
      +  "linkedin_ads"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / adAccountId / pattern
      Previous value: -"^act_\\d+$"New value: +"^(act_)?\\d+$"
    • addedInput schema / properties / level
      Added value: +{
      +  "enum": [
      +    "campaign",
      +    "ad_group",
      +    "ad"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / platform
      Added value: +{
      +  "description": "meta_ads or tiktok_ads. Needed only when the profile has both ad networks and no accountId is given.",
      +  "enum": [
      +    "meta_ads",
      +    "tiktok_ads"
      +  ],
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedInput schema / properties / accountId / description
      Previous value: -"The Facebook accountId from list_accounts. Defaults to the profile's Facebook connection."New value: +"The Facebook accountId from list_accounts. Without it, pass profileId to use that profile's Facebook connection."
    • changedInput schema / properties / profileId / description
      Previous value: -"Defaults to the profile your API key is bound to."New value: +"A profileId from list_profiles. Optional when accountId is given, which names its profile; if both are given they must agree."
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint and openWorldHint, but the description goes well beyond them: it discloses that ACTIVE spends real money, that setting an existing status is a no-op, the four-per-hour status change limit, Meta-side pacing to avoid looking automated, the retryAfterSeconds contract, and a cross-object side effect (activating a LinkedIn draft campaign group also activates its campaign). This is unusually rich behavioral disclosure for a mutation tool.

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 what the tool does, then risk, then rate-limit handling — a sensible priority order. Dense but nearly every clause carries distinct information; the nested parenthetical of platform object names and the density of constraints cost it a point.

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 an 8-parameter destructive mutation with no output schema, the description covers the highest-stakes gaps: financial risk, idempotency, rate limits, retry behavior, and side effects. The remaining gap is identification of the target object (objectId vs adAccountId vs campaignRecordId), which is left to a partially-documented schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 38%, and the description compensates partially by explaining the conditional need for 'level' (TikTok and LinkedIn only) and the ACTIVE/PAUSED semantics. It says nothing about objectId, adAccountId, campaignRecordId, or the accountId/profileId fallback, which the schema only partly covers.

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 ('Set a campaign, ad set ... or ad to ACTIVE or PAUSED') and disambiguates the object hierarchy with platform-specific parentheticals (TikTok ad group, LinkedIn campaign). An agent can tell this is a status-only mutation rather than a general update, distinct from siblings like ads_update_campaign.

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?

Explicit when-to-use conditions ('TikTok and LinkedIn need level'), hard exclusions ('never activate without the user's explicit confirmation of the budget and dates'), anti-patterns ('do not toggle it on and off'), and an error-handling branch ('on ads_change_limited, wait retryAfterSeconds before retrying'). Little is left to inference.

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