Skip to main content
Glama

Get Account Activities

adsap_get_account_activities

Retrieve the change log of a Meta ad account: who changed what, when, and with which app. Covers budget, status, creative, targeting, creation, deletion, billing and policy events. Use it to tie a performance change to an edit (e.g. CPA rose after a budget increase) or to answer "was this changed in Ads Manager or through Adsap?". APP: each event's app_name is the app Meta recorded for the change. "ADSAP" = made through Adsap (the web app or this assistant; Meta does not tell the two apart). "Power Editor" = Ads Manager on a computer (Meta's old name for it). "Ads Manager App for iOS" = the Ads Manager iPhone app. "ads MCP server" = Meta's own Ads connector. Any other name = another app connected to the account or a Meta internal tool. null = no app: a change Meta made itself (actor_name "Meta"). summary.by_app counts events per app. FILTERS: ad_set_id (the ad set and all its ads) or ad_id (one ad), and event_type_filter (creative_change = an ad's text, image or video was replaced). Filters scan the WHOLE days_back window, then the newest limit matching events come back; summary.window_truncated=true means the account had more activity than could be scanned, so the OLDEST part of the window may be incomplete. Creative changes carry extra_data.old_creative_id and extra_data.new_creative_id (the ad's creative before and after), never image links. VOCABULARY: object_type is translated (campaign / ad_set / ad), but extra_data keeps Meta's legacy words: inside extra_data 'campaign' means AD SET and 'adgroup' means AD (e.g. extra_data.campaign_id on an ad event is the ad's parent AD SET id, not a campaign id).

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": {
      "ad_account_id": "<ad_account_id>"
    },
    "name": "adsap_get_account_activities"
  }
}

Input Schema

NameRequiredDescriptionDefault
ad_idNoOnly this ad. Not together with ad_set_id.
limitNoMax events returned AFTER filtering, newest first. Default 100, max 500.
ad_set_idNoOnly this ad set and all its ads. Not together with ad_id.
days_backNoDays of history. Default 7, max 30.
ad_account_idYesMust include act_ prefix.
event_type_filterNoFilter by change type, applied across the whole days_back window. creative_change = an ad's text, image or video was replaced. targeting_change = an ad set's audience or placements. status_change = paused, activated, or moved through review. budget_change includes bid strategy and spend limits. Default: all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / ad_id
      Added value: +{
      +  "description": "Only this ad. Not together with ad_set_id.",
      +  "pattern": "^\\d+$",
      +  "type": "string"
      +}
    • addedInput schema / properties / ad_set_id
      Added value: +{
      +  "description": "Only this ad set and all its ads. Not together with ad_id.",
      +  "pattern": "^\\d+$",
      +  "type": "string"
      +}
    • changedInput schema / properties / event_type_filter / description
      Previous value: -"Filter by event types, applied across the whole days_back window. Default: all."New value: +"Filter by change type, applied across the whole days_back window. creative_change = an ad's text, image or video was replaced. targeting_change = an ad set's audience or placements. status_change = paused, activated, or moved through review. budget_change includes bid strategy and spend limits. Default: all."
    • changedInput schema / properties / event_type_filter / items / enum
      Previous value: -[
      -  "budget_change",
      -  "status_change",
      -  "creation",
      -  "deletion",
      -  "billing",
      -  "policy",
      -  "all"
      -]New value: +[
      +  "budget_change",
      +  "status_change",
      +  "creative_change",
      +  "targeting_change",
      +  "creation",
      +  "deletion",
      +  "billing",
      +  "policy",
      +  "all"
      +]
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does so well: it discloses that filters scan the entire days_back window before the newest `limit` matches are returned, and that summary.window_truncated=true means the oldest part of the window may be incomplete. It also pre-empts two interpretation traps (app_name null = Meta-made change; extra_data uses Meta's legacy vocabulary where 'campaign' means AD SET).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and use cases are correctly front-loaded, and the FILTERS/VOCABULARY sectioning aids scanning. However the app_name glossary enumerates five app-name strings plus a null case inline, which is bulk that could be tightened without losing decision-relevant information.

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?

With no output schema, the description still explains the returned shapes that matter: summary.by_app counts, summary.window_truncated, and extra_data.old_creative_id/new_creative_id on creative events (plus the note that image links are never included). Combined with the filter and vocabulary notes, an agent has everything needed to call and interpret this tool.

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 each parameter is already documented, but the description adds genuine meaning the schema lacks: the interaction between filters and limit (whole-window scan, then newest matches), and the consequence flagged via window_truncated. The ad_set_id/ad_id mutual exclusion is only in the schema, so the description doesn't fully compensate for that, keeping it below 5.

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?

Opens with a precise verb+resource+scope: the change log of a Meta ad account, covering who/what/when/which app, and enumerates the event families it spans (budget, status, creative, targeting, creation, deletion, billing, policy). This clearly separates it from the analytics siblings like adsap_get_insights or adsap_get_account_health.

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?

Gives two concrete use cases (tie a CPA rise to a budget increase; determine whether a change came from Ads Manager or Adsap) that make the right invocation obvious. It does not name a specific sibling to use instead when the agent actually wants performance data rather than change history, so it stops short of explicit routing.

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