Skip to main content
Glama

Save a funnel

funnels_save
Destructive

Save a funnel you mapped from the site's code: the path most visitors take toward signing up or paying from one of the most visited pages (find those with analytics page_flow: the top pages, where visitors go next, what they click). Each step is a goal's definition: PAGEVIEW (a path, * for a wildcard), EVENT (an event name, or name@/path such as form_submit@/register, which t.js sends with no code on the site), CTA (the element's data-sf value, * for a wildcard), ENGAGED, REVENUE (trial, paid) or CHECKOUT (a visit back from a hosted checkout). Put other ways that count as the same step in any (a signup step holds every way in that goals_save mapped: the form and the page a new GitHub or Google account lands on), and where you found each step in evidence (file:line). Steps count in order (strict, the default) within windowDays (default 7). The same name redefines a funnel; remove: true deletes it. It is counted from events already stored, so it returns its last 28 days at once: a step no one reached is usually a wrong pattern. Free.

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": {
      "name": "<name>"
    },
    "name": "funnels_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesWhat the path is, e.g. "Home to signup", "Pricing to payment", "Free tool to signup"
stepsNoNeeded unless remove
removeNo
siteIdNo
strictNoSteps in this order (default true)
windowDaysNoDays from the first step to the last (default 7)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description earns real credit by explaining exactly what is destructive (same-name redefinition, remove:true) and that results are computed retroactively over 28 days of stored events so an unreached step signals a bad pattern. This is strong on behavior, but it doesn't say whether save is idempotent per-site, who may delete, or what the response body contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is largely substantive, but everything is packed into a few long, parenthetical-heavy sentences that are hard to scan on first read (e.g., the form_submit@/register aside). It is front-loaded with purpose, yet the step-type enumeration and examples could be split or bulleted for far faster parsing.

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 6-parameter mutation with nested step objects and no output schema, the description covers creation, redefinition, deletion, step ordering, and the fact that it returns 28 days of results immediately. Gaps remain around siteId, the 2-8 step bounds, and the shape of what comes back, but the essential calling knowledge is present.

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?

With 67% schema coverage, the description compensates well: it defines what each step type matches (PAGEVIEW paths with '*', EVENT name or name@/path, CTA data-sf value, ENGAGED, REVENUE trial/paid, CHECKOUT), explains `any` as alternate ways of the same step with a concrete signup example, and gives `evidence` as file:line. It also restates defaults for strict and windowDays in plain terms.

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 description opens with a specific verb+resource ('Save a funnel you mapped from the site's code') and even defines what a funnel is (the path most visitors take toward signup/payment). It references goals_save for step semantics, giving partial sibling differentiation, though it never contrasts with funnel_check or explains how saving relates to checking.

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 tells the agent where the input comes from (analytics page_flow: top pages, next steps, clicks) and states redefinition/deletion semantics ('The same name redefines a funnel; remove: true deletes it'). What's missing is routing guidance against funnel_check, which an agent could reasonably reach for instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.