Marsell

Get the analytics

get_analytics

Read-only

Reads what the Analytics place shows for one project: every number Marsell holds over the days asked (sales, visits, followers, views and the rest, each with where it came from; leavesOutTeam on Stripe's count of new customers, which leaves out the business's own team, while the money counts every payment and subscription, the team's own included; Stripe's revenue is before tax wherever Stripe gives the tax), which of them lead for this kind of project (leads: its goal's number first; a free tool leads with downloads and stars, never money), what nothing counts yet with the owner's next step, what people searched for, the site's pages as Google Search showed them, the business's reviews on Google, the posts that went out in the span with their pictures and reach, the business's own channel and code project with their numbers, and its own site's visits read now. Where people press on the site and Google Analytics' own count are not in it: they are on the Analytics place. Nothing is spent. One number day by day is metrics_series, what each piece of work brought outcomes_summary, what each ad brought ad_results_read.

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": "get_analytics"
  }
}

Input Schema

Name	Required	Description	Default
`days`	No	The span, in days ending today. 30 when left out.
`project`	No	The project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint false, and destructiveHint false, so the safety profile is covered. The description adds meaningful behavior: 'Nothing is spent', Stripe counting caveats (new customers exclude the team, revenue is before tax where available), project-type-specific lead metrics, and explicit exclusions. It does not discuss permissions or data freshness beyond 'read now' for site visits, so it is strong but not maximal.

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 purpose is front-loaded, but the bulk of the description is a long run-on sentence with nested parentheses and semicolon-separated caveats that is difficult to parse. Much of the detail is useful, yet the structure could be tightened and segmented without losing meaning.

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 read-only analytics aggregation with no output schema, the description lists the data families returned, important counting caveats, exclusions, and related sibling tools. It does not describe the response shape or ordering, but the input schema and annotations cover inputs and safety, making the definition largely complete for correct invocation.

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% and both parameters are fully documented in the schema (days with an enum and default, project id or exact name with the single-project case). The description only echoes 'over the days asked' and 'for one project' without adding format, edge-case, or validation semantics beyond what the schema already provides, so baseline 3 applies.

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?

The description opens with a specific verb and resource: 'Reads what the Analytics place shows for one project', then enumerates the data domains (sales, visits, followers, views, reviews, posts, site visits) and explicitly distinguishes this tool from metrics_series, outcomes_summary, and ad_results_read. An agent can tell what the tool returns and how it differs from the analytics-related siblings.

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 routes narrower needs to specific siblings — metrics_series for one number day by day, outcomes_summary for work outcomes, ad_results_read for ad results — and states exclusions (heatmaps and Google Analytics' own count are not included here). It lacks an explicit 'use this when...' statement and does not compare against other broader reads like get_overview, but the alternative guidance is clear.

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

All Marsell 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.