Skip to main content
Glama

ga4_funnel

Build sequential GA4 event funnels that count users completing each step in order, show per-step completion and abandonment rates, and optionally split results by a dimension.

Instructions

Sequential funnel over GA4 events (Data API runFunnelReport, v1alpha): counts users who completed each step in order, with completion and abandonment rates per step. Optionally broken down by a dimension such as platform. The endpoint is alpha and can return user counts that disagree with ga4_event_counts for the same events and dates (for example more users at a step than ever fired its event): cross-check before reporting. Requires: Google Analytics Data API (analyticsdata.googleapis.com) enabled on the quota project; Lector (Viewer) en la propiedad de GA4. If it fails for access, the error explains how to fix it; ga4_check_access checks everything at once.

Input Schema

NameRequiredDescriptionDefault
stepsYesEvent names in funnel order
end_dateYesEnd date: YYYY-MM-DD, or relative like "today"
propertyNoSaved property name (see ga4_list_properties). Defaults to the default property.
breakdownNoDimension API name to split the funnel by, e.g. "platform"
start_dateYesStart date: YYYY-MM-DD, or relative like "7daysAgo", "yesterday", "today"
open_funnelNoIf true, users can enter at any step; if false (default), they must start at step 1
breakdown_limitNoMax breakdown values (default 5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that the endpoint is v1alpha and can return user counts that disagree with ga4_event_counts (even more users at a step than ever fired the event), and it warns to cross-check. It also names prerequisites — Data API enabled on the quota project and Viewer role on the property — and states that access errors are self-explanatory.

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?

Purpose is front-loaded in the first sentence and the caveats follow in a logical order: output shape, alpha warning, prerequisites, error handling. It is somewhat dense and contains an inconsistent language fragment ('Lector (Viewer) en la propiedad de GA4') that slightly interrupts flow, but no sentence is wasted.

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 seven-parameter analytics tool with no output schema and no annotations, the description covers what the tool returns, the alpha reliability caveat, the prerequisites, and where to go for access troubleshooting. An agent has enough to call it correctly and to interpret suspicious results.

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 description coverage is 100%, so all seven parameters, including steps ordering, open_funnel semantics, and breakdown_limit bounds, are already documented in the schema. The description only echoes the optional breakdown concept ('such as platform') without adding format or constraint detail beyond that. Baseline 3 is appropriate.

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 — a sequential funnel over GA4 events via runFunnelReport — and specifies exactly what is produced: per-step user counts with completion and abandonment rates, optionally split by a dimension. This is clearly distinguishable from siblings like ga4_step_conversion, ga4_event_counts, or ga4_run_report.

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 concrete routing advice: cross-check against ga4_event_counts before reporting, and use ga4_check_access if access fails. It does not explicitly contrast with the closest sibling ga4_step_conversion, so the agent must infer which funnel-style tool to pick, but the surrounding guidance is strong.

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