shopify-chatgpt-ads-mcp

Overview Schema Source Related Servers Discussions Admin

Performance report

get_insights

Read-only

Retrieves OpenAI Ads performance insights for accounts, campaigns, ad groups, or ads over a date range, including impressions, clicks, spend, CTR, CPC, CPM, conversions, attributed sales, and ROAS.

Instructions

OpenAI's Insights for the account, a campaign, an ad group or an ad: impressions, clicks, spend, CTR, CPC, CPM and, without a breakdown, conversions, attributed sales and ROAS. Attribution settings are always sent explicitly (defaults 30-day click, 1-day view, ad_event_time, which is what Ads Manager shows). spend/cpc/cpm are MAJOR units of the account currency, not micros. A missing or null metric is unavailable, never zero. Conversions update daily; allow a day. These are OpenAI's attributed numbers; for orders measured in the store use the measurement_* tools.

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "get_insights"
  }
}

Input Schema

Name	Required	Description
`id`	No	Required unless scope is account
`to`	Yes	Last day, inclusive (YYYY-MM-DD, ad account timezone)
`from`	Yes	First day (YYYY-MM-DD, ad account timezone)
`after`	No	next_after of the previous page
`level`	No	What one row is. Default: campaign for account scope, else the scope itself
`limit`	No	Rows per page, default 500
`scope`	No	Default account
`breakdown`	No	One extra dimension (delivery metrics only). product keeps about 30 days of history
`time_basis`	No
`granularity`	No	Default daily; none = one total per row
`view_window_days`	No
`click_window_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare readOnly/openWorld/non-destructive; the description adds substantive behavior beyond that: attribution windows are always sent explicitly with stated defaults (30-day click, 1-day view, ad_event_time matching Ads Manager), spend/cpc/cpm are in major currency units rather than micros, and null means unavailable rather than zero. It also discloses freshness (conversions lag ~1 day) and breakdown limits (delivery metrics only, product retains ~30 days), which an agent cannot get from annotations or schema.

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

Conciseness5/5

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

Front-loaded with what the tool returns, then progressively narrower caveats (attribution defaults, units, null semantics, freshness, sibling routing). No sentence is redundant with the schema or annotations; the parenthetical notes are dense but each carries a distinct invariant.

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?

For a 12-parameter reporting tool with no output schema, the description carries the burden of describing the returned metric set and does so explicitly. Combined with the units, null and latency disclosures, an agent has enough to call it and interpret results without guessing.

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 75% schema coverage the baseline is already solid, and the description adds real meaning on top: it pins down the defaults behind click_window_days, view_window_days and time_basis, and constrains breakdown to delivery metrics with a note on product history length. It does not clarify how scope and level interact or the id requirement, which remain schema-only.

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?

The description names the exact resource (Insights for account/campaign/ad group/ad) and enumerates the metric set returned: impressions, clicks, spend, CTR, CPC, CPM, plus conversions, attributed sales and ROAS when no breakdown is applied. It also draws a hard boundary against the measurement_* siblings, so an agent can pick the right tool 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?

It gives an explicit routing rule for the closest alternative: 'for orders measured in the store use the measurement_* tools', which is the most likely confusion point given ten measurement_* siblings. It stops short of guidance on when to prefer a breakdown, a specific level, or granularity, so selection within this tool is still inferred from the schema rather than stated.

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

Deploy Server