Quattr

funnel_dropoff

Read-only

Where do users drop off in the funnel? Given an ORDERED list of funnel steps (each an existing web-analytics count metric — e.g. sessions → conversions → transactions), returns each step's count, the per-step drop-off rate, and the biggest-leak step (the largest single drop). Use for "where do users fall out of the funnel?", "which step leaks the most?". Each step carries its metric's own QWA default scope (echoed as appliedScope): behavioral steps are web + google/organic, conversion/transaction steps are web + All traffic sources (QWA's own auto-switch) — a mixed funnel discloses that cross-scope legs compare different populations. This is an observational macro-funnel over GA count metrics (GA4 / Adobe), NOT a per-event step sequence (no event-level funnel breakdown exists yet). Whole-domain only in v1.

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": {
      "date_range": "<date_range>",
      "steps": "<steps>"
    },
    "name": "funnel_dropoff"
  }
}

Input Schema

Name	Required	Description
`steps`	Yes	The ordered funnel steps, top to bottom (at least 2). Each step is an existing count metric — e.g. [{metric:"sessions"},{metric:"conversions"},{metric:"transactions"}]. Drop-off is computed between consecutive steps in this order.
`segment`	No	Tracked segment ID; defaults to "default" (whole domain). Per-segment web analytics is not yet available — non-default returns an honest note.
`date_range`	Yes	Explicit date range, e.g. "2026-05-01 to 2026-05-31". Both endpoints are INCLUSIVE — the END day is covered (a 7-day range = 7 days). Quattr weeks run Sunday–Saturday; for "last week" use the most recent complete Sun–Sat span.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safe-read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), yet the description adds genuinely non-obvious behavior: each step inherits its metric's own default scope, mixed funnels compare different populations across legs, and non-default segments return an honest note rather than data. These are exactly the caveats an agent needs to avoid misreading results.

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 the core question before the mechanics, and nearly every sentence carries distinct information. The scope paragraph is dense with internal jargon (QWA default scope, auto-switch) that slows parsing, so it is efficient but not maximally clean.

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 carries the full burden and does so: it names the returned artifacts (counts, drop-off rates, biggest leak, appliedScope) and closes the main failure modes (mixed populations, unsupported segments, whole-domain-only v1). Nothing essential for correct invocation is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by framing steps as ordered count metrics, explaining that scope is attached per step and echoed as appliedScope, and flagging that per-segment analysis is unavailable. The date_range semantics are left to the schema, which already documents inclusivity.

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 analytical verb and resource ('where do users drop off in the funnel') and enumerates the exact outputs: each step's count, per-step drop-off rate, and the biggest-leak step. It also declares what it is not ('NOT a per-event step sequence'), which cleanly separates it from any sibling that might be confused with funnel work.

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 triggering questions ('where do users fall out of the funnel?', 'which step leaks the most?') and a hard exclusion (not event-level step sequences, whole-domain only in v1). Clear context, but it never names a sibling tool to use instead when the request falls outside these bounds, so it stops short of explicit alternative routing.

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

All Quattr 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?