AdsAgent — TikTok Ads MCP

Read product attribution totals

mmp_insights_query_product_event_summary

Read-only

Read AppsFlyer count, unique-user, and revenue aggregates for one saved product/event over an inclusive range of at most 90 days. The server fixes channel_pid=tiktokglobal_int and delegates to the Meta-owned product/MMP service, preserving its completeness and source-coverage fields. Do not fan out by date or channel.

REQUIRED: product_id (the product_ref from products_list), event_name, date_from, date_to. DATE PARAMS use YYYY-MM-DD. Detail rows are capped at 1000 rows and 256KiB; when truncated=true pass next_cursor back as cursor. Optional breakdown: country, placement, campaign, adset, or ad. adset is an AppsFlyer adapter field for TikTok's native ad_group role. EXAMPLE: mmp_insights_query_product_event_summary({"product_id": "<product_ref>", "event_name": "purchase", "date_from": "2026-07-01", "date_to": "2026-07-07"})

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cursor`	No
`date_to`	Yes
`breakdown`	No
`date_from`	Yes
`event_name`	Yes
`product_id`	Yes
`connection_context`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

addedInput schema / properties / cursor

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Cursor"
+}

Changed1 schema field changedOct 13, 2026
- addedInput schema / properties / connection_context
```
Added value: +{
+  "pattern": "^mctx_v1_[0-9a-f]{64}$",
+  "type": "string"
+}
```
First observedSep 17, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true/destructiveHint=false, so safety is covered; the description adds real behavioral context beyond that: the server pins channel_pid=tiktokglobal_int, delegates to the Meta-owned MMP service, preserves completeness and source-coverage fields, and caps detail rows at 1000 rows/256KiB with truncation surfaced via next_cursor.

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 purpose, then uses REQUIRED/date-format and EXAMPLE blocks to organize dense content; every sentence carries information the schema does not. It is somewhat packed (delegation, completeness fields, caps, cursor, breakdown nuances in one block), but there is little dead weight.

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 tells the agent what comes back (completeness and source-coverage fields), how results are bounded (1000 rows/256KiB), and how to continue (pass next_cursor as cursor). Constraints, required inputs, and an example are all present, so nothing essential is missing for correct invocation.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does so: it enumerates the four required params, fixes the YYYY-MM-DD date format, explains cursor semantics on truncation, and clarifies the breakdown enum (including that 'adset' maps to TikTok's native ad_group role). This is meaning well beyond the bare schema.

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 AppsFlyer count, unique-user, and revenue aggregates for one saved product/event. It scopes the operation tightly (single product/event, inclusive range ≤90 days) and implicitly distinguishes itself from the sibling mmp_insights_get_product_event_today and the broader insights_query_* family.

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 operating context: an inclusive range capped at 90 days and an explicit 'Do not fan out by date or channel' exclusion. It does not name a competing sibling (e.g. the 'today' variant) or state the condition that selects one over the other, so routing between MMP insights tools is still partly inferred.

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

All AdsAgent — TikTok Ads MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?