Skip to main content
Glama

Track events from outside the site

analytics_track

Record what happened away from the site's pages: a Shopify order, a deal won, a call that booked a demo, a renewal. Up to 100 at once, each with props and revenue. An event joins the visit that led to it when you give the visitor's IP address and user agent (a Shopify order carries both; they find the visit and are never kept), or the email or contact of a person whose first visit Conecto kept; otherwise it counts without a source. Then analytics_breakdown shows which channels and campaigns bring the money. Don't track what the site itself already sends, or it counts twice. Free; each event counts toward the site's monthly events. 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": {
      "site": "<site>",
      "events": "<events>"
    },
    "name": "analytics_track"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesThe site's domain (e.g. halversoncycle.example) or its site_id.
eventsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavior: batches of up to 100, attribution via visitor IP/user agent or email/contact, that IP and user agent are used once and never kept, that unattributed events still count, the double-counting risk, and the monthly event quota impact. This is rich context for a non-idempotent mutation tool.

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?

The content is front-loaded and mostly earns its space, moving from purpose to batching, attribution, analysis, deduplication, and cost. The ending repeats 'Free' twice, which is a small structural flaw in an otherwise efficient description.

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 mutation tool with no output schema, the description covers the essential context: what gets recorded, how events are attributed, what is not retained, how to avoid double counting, and the quota implication. An agent has enough information to invoke it correctly without needing return-value documentation.

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?

Although schema description coverage is only 50%, the description adds substantial semantics for the events array: batch size, props and revenue, visitor IP/user agent for attribution, and email/contact crediting to a person's first visit. It does not document every field such as at, page, or currency, but it compensates well for the most consequential parameters.

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 states a specific verb and resource: recording events that happened away from the site's pages. It gives concrete examples (Shopify order, deal won, booked demo, renewal) and explicitly distinguishes this from events the site itself sends, which differentiates it from the site-event family even without naming a sibling.

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 clearly says when to use the tool — offline/backend events such as orders, deals, calls, and renewals — and includes an explicit when-not condition: don't track what the site already sends because it will count twice. However, it does not name analytics_add_events as the alternative for on-site events, leaving the sibling choice partly implicit.

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.

Resources