Skip to main content
Glama
Upload-Post

Upload-Post

Official

Read ChatGPT Ads

chatgpt_ads_read
Read-only

Read connected ChatGPT Ads data—campaigns, ad groups, ads, and performance insights—without changing or spending anything. Review ad status and pull spend, click, and impression metrics.

Instructions

Read-only ChatGPT Ads (OpenAI's ad platform) data of the ad account the user connected to Upload-Post in the dashboard; spending on it runs on the user's own OpenAI billing. Nothing here changes or spends anything. accounts (connected ad accounts, default first, with their linked profiles; never the key); account (live metadata of the chosen account); campaigns; campaign (campaign_id); ad_groups (campaign_id required); ad_group (ad_group_id); ads (ad_group_id required; each ad has review_status in_review|approved|rejected); ad (ad_id); lists take params limit (1-500, default 20), after (last_id of the previous page), before, order asc|desc. insights (whole account), campaign_insights (campaign_id), ad_group_insights (ad_group_id), ad_insights (ad_id): params since / until (YYYY-MM-DD, ad account timezone), time_granularity hourly|daily|monthly|none (default daily), aggregation_level ad_account|campaign|ad_group|ad, fields (list: impressions, clicks, spend, ctr, cpc, cpm and more), segments (list: product, country, device), filters / sort / time_ranges (lists of objects, passed to OpenAI), limit (1-2000), after, before. preview_ad (ad_id): a temporary preview link of the ad, valid 24 hours. 404 means no ChatGPT Ads account is connected, the profile has none linked, or the object does not exist; 401 can also mean OpenAI revoked the stored key and the account has to be reconnected in the dashboard.

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": {
      "action": "<action>"
    },
    "name": "chatgpt_ads_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
ad_idNoThe ad (ad, ad_insights, preview_ad, update/activate/pause/archive_ad).
actionYes
paramsNoOther API fields for this action, with the REST API's own names (snake_case) and shapes. Paging and insights fields, as listed for each action. Leave out what you do not want to change.
ad_group_idNoThe ad group (ad_group, ad_group_insights, update/activate/pause/archive_ad_group; ads lists the ads of this group; create_ad puts the ad in it).
campaign_idNoThe campaign (campaign, campaign_insights, update/activate/pause/archive_campaign; ad_groups lists the groups of this campaign; create_ad_group puts the group in it).
ad_account_idNoConnected ad account to use (`adacct_...`, from chatgpt_ads_read accounts). Without it and without profile_username: the default account.
profile_usernameNoUse the ad account linked to this Upload-Post profile, and only that one.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.26.5

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered structurally. The description still adds real value beyond them: spending runs on the user's own OpenAI billing, preview links expire in 24 hours, and 401 can mean OpenAI revoked the stored key requiring dashboard reconnection. That is solid added context, though return shapes and rate-limit behavior are not discussed.

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 is front-loaded in the first clause, which is good, but the body is a single semicolon-chained run-on that mixes action routing, parameter defaults, and error codes without line breaks or grouping. Every element is useful, yet the density makes it harder to scan than it needs to be.

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?

An output schema exists, so return values need not be described, and the description covers required ids per action, defaults, and error semantics. What remains thin is the structure of the nested filter/sort/time_ranges objects and how the account/profile_username selection interacts with the accounts action.

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?

The schema's params object is a free-form additionalProperties bag, so the description is the primary source of meaning for paging and insights fields: limit ranges (1-500 default 20, 1-2000 for insights), after as "last_id of the previous page," order asc|desc, time_granularity defaults, timezone for since/until, and the fields/segments/filters lists. It adds substantial meaning beyond the 86% schema coverage, though it does not explain the shape of the filters/sort/time_ranges objects.

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 ("Read-only ChatGPT Ads ... data of the ad account the user connected") and immediately bounds the scope with "Nothing here changes or spends anything," which separates it from the write-side sibling manage_chatgpt_ads. The action enumeration (accounts, campaigns, ads, insights, preview_ad) makes the surface concrete.

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 clear context for when to use it: read-only access, per-action required ids ("ad_groups (campaign_id required)", "ads (ad_group_id required)"), and troubleshooting routing for 404/401. It stops short of explicitly naming manage_chatgpt_ads as the alternative for mutations, leaving that inference to the reader.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools