AdLoop

Analytics funnel report

run_ga4_funnel

Read-only

Run a GA4 funnel report: how many users go from one step to the next, and where they drop off.

Steps are event names or pages, in order. Returns per step the users, completion rate to the next step, abandonments and abandonment rate, plus how many started and finished, the overall completion rate and the biggest drop (after which step most users leave). With breakdown, the same per value of a dimension (e.g. deviceCategory); with next_action, the most common next event or page after each step, i.e. what users do instead. Uses the GA4 Data API v1alpha (runFunnelReport), the endpoint behind GA4's funnel explorations; data reaches back as far as the property's data retention.

Google Analytics Data API: https://developers.google.com/analytics/devguides/reporting/data/v1 and Admin API: https://developers.google.com/analytics/devguides/config/admin/v1

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "run_ga4_funnel"
  }
}

Input Schema

Name	Required	Description	Default
`steps`	No	2 to 10 steps. Each is an event name ("add_to_cart") or an object: {"event": "purchase", "name": "Bought"}, {"page": "/checkout"} (page views whose URL contains the text), optional "directly_followed": true (no other event in between) and "within_minutes": 30 (must follow the previous step within that time).
`breakdown`	No	Dimension to split every step by, e.g. deviceCategory, sessionDefaultChannelGroup, country.
`next_action`	No	Dimension for "what came next" after each step, e.g. eventName or pagePath.
`open_funnel`	No	False (default) counts only users who start at step 1; true lets users enter at any step.
`property_id`	No	GA4 property as "properties/123456789" or the bare numeric ID. If empty, uses the default from config.
`date_range_end`	No	Same formats.	today
`breakdown_limit`	No	How many values of the breakdown dimension (1-15).
`date_range_start`	No	"today", "yesterday", "NdaysAgo" or "YYYY-MM-DD".	28daysAgo
`dimension_filter`	No	Only count users matching these conditions, same format as in run_ga4_report, e.g. [{"field": "deviceCategory", "value": "mobile"}].

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real context beyond that: the underlying endpoint (runFunnelReport in Data API v1alpha, the engine behind funnel explorations) and the constraint that data only reaches back as far as the property's data retention.

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 a one-line purpose, then a dense but well-ordered paragraph on steps, outputs, and options. The closing API/documentation links are slightly boilerplate but short; nothing is wasted enough to hurt readability.

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 a 9-parameter tool with 0 required params and full schema coverage, the description covers purpose, data source, retention limits, and the meaning of the two optional modes. With an output schema present it need not enumerate return fields, though it does so anyway, so an agent has enough to call it correctly.

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 coverage is 100%, so the baseline is 3. The description does add interpretive value by explaining how breakdown and next_action change the shape of the result and that steps may be events or pages, but most per-parameter mechanics (formats, 2-10 step limits, directly_followed/within_minutes) live in the schema, not the description.

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 specific verb and resource ("Run a GA4 funnel report") and immediately states the semantics: "how many users go from one step to the next, and where they drop off." That is clearly distinguishable from the generic sibling run_ga4_report without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains what each option does (breakdown splits every step by a dimension, next_action shows what users do instead, open_funnel allows entry at any step), which implies when to reach for each. But it never explicitly says when to use this tool rather than run_ga4_report or run_ga4_attribution, nor any prerequisites beyond the data-retention note.

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

All AdLoop 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.