Skip to main content
Glama
Sign In

invisit

by dev.invisit
OverviewDiscussionsAdmin

Run a funnel

run_funnel
Read-onlyIdempotent

How many visits went through steps in order, and where they dropped off. A step starting with "/" is a page path; anything else is a custom event name. Pass 2-8 steps, or the name or id of a saved funnel (omit both to list saved funnels).

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": {
      "site_id": "<site_id>"
    },
    "name": "run_funnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLast day, inclusive, YYYY-MM-DD; default today
fromNoFirst day, YYYY-MM-DD; overrides period
stepsNo
funnelNoName or id of a saved funnel
periodNoWindow ending now; days are whole days in the timezone. Ignored when from is set.30d
filtersNoKeep only matching traffic; values of one dimension are OR-ed, dimensions AND-ed
site_idYessite_id from list_sites; a site name, slug or domain also resolves
timezoneNoIANA zone for day boundaries; default the user's
breakdownNoSplit conversion by this

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare this is a read-only, idempotent, non-destructive query, so the bar is lower. The description adds real behavior beyond that: steps must be traversed in order, partial traversal is reported as drop-off, and the tool silently switches to a listing mode when neither steps nor funnel is supplied — a mode change an agent would otherwise not anticipate.

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?

Three sentences, zero filler, and the outcome (counts plus drop-off) is front-loaded before the input conventions. Each sentence carries distinct information: what is computed, how steps are interpreted, and how the input modes work.

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?

With nine parameters, no output schema, and a quirky polymorphic input, the description covers the pieces most likely to cause a wrong call: step string semantics and the steps-vs-saved-funnel-vs-list branching. It does not describe the response shape (per-step counts, drop-off fields) or interaction between filters/breakdown and funnel results, which is the main remaining gap.

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 89%, so most parameters (period, from/to, filters, timezone, breakdown) are already documented in the schema and the description stays silent on them. It does add genuine meaning for the one under-documented parameter, steps: the leading-slash page-path versus custom-event-name convention is not in the schema at all, and the steps/funnel mutual exclusivity is stated. Useful but narrow.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb and resource: counting visits through ordered funnel steps and reporting drop-off. That distinguishes it from aggregation siblings like get_breakdown and get_timeseries, though no sibling is named explicitly.

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 concrete mode-selection rules: pass 2-8 steps for an ad-hoc funnel, or a saved funnel name/id, and omit both to list saved funnels instead of running one. What is missing is guidance on when to prefer this over get_breakdown for multi-step analysis, but the input-mode branching is unusually clear.

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

All invisit toolsInspect
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