Skip to main content
Glama

Visibility Genies

Read key events

get_google_analytics_key_events
Read-only

Key event counts from Google Analytics, by event or by event and landing page, optionally compared with the previous period. Organic Search by default. Read only and 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": {
      "projectId": "<projectId>"
    },
    "name": "get_google_analytics_key_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
deviceNoOnly this device: desktop, mobile or tablet.
mediumNoOnly sessions whose medium contains this text, in any case.
offsetNo
sourceNoOnly sessions whose source contains this text, in any case.
channelNoWhich traffic to read: Organic Search only (default) or all.organic_search
countryNoOnly this country, as its two-letter ISO code, for example DE.
endDateNoInclusive date as YYYY-MM-DD. Give both startDate and endDate, or neither for the last 28 complete property days.
campaignNoOnly sessions whose campaign contains this text, in any case.
keyEventNoCount only this key event (for example purchase) in the key event columns, instead of all key events. Not for the key events report, which lists them by name.
breakdownNoCount key events by event name, or by event and landing page.event
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
startDateNoInclusive date as YYYY-MM-DD. Give both startDate and endDate, or neither for the last 28 complete property days.
channelGroupNoOnly this Google default channel group by its exact name, for example Paid Search, Organic Social or AI Assistant. Pass channel=all where the tool has it, or Organic Search is all that is read.
pageContainsNoOnly pages whose address contains this text, in any case. Not for site search or ecommerce by item.
comparePreviousPeriodNoAlso read the period just before and compare the rows.

Output Schema

NameRequiredDescriptionDefault
rowsNo
errorNo
quotaNo
sourceNo
statusYes
requestNo
pageInfoNo
rowCountNo
warningsNo
comparisonNo
diagnosticsNo
totalRowCountNo
reportMetadataNo
ecommerceActivityNo
diagnosticCoverageNo
siteSearchActivityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true; the description's "Read only and free" restates the safety profile in part but adds the genuinely new cost/billing signal ("free"). The default organic-only scope is a meaningful behavioral disclosure, and the optional previous-period comparison is flagged. Still missing: result-size behavior (limit default 100, max 1000), pagination expectations for a 16-parameter report, and what happens when no data matches.

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?

Three short sentences, front-loaded with what is returned, then breakdown granularity, then comparison capability and scope. Every clause carries information; the only minor waste is "Read only," which duplicates readOnlyHint, though "free" alongside it is not redundant.

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 16 parameters, a 1-required-parameter shape, high schema coverage, an output schema, and full annotations, the description need only set scope and defaults — which it does. The remaining gap is that it does not warn about the organic-only default being easy to miss when an agent wants all traffic, nor about volume/pagination behavior for a large report.

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 88%, so the schema already explains nearly every parameter including date pairing, ISO country codes, and the keyEvent exclusion. The description nevertheless adds cross-parameter meaning — that breakdown can be by event alone or event plus landing page, that the previous-period comparison is optional, and that Organic Search is the implicit default filter set. That framing helps an agent reason about defaults rather than read 16 fields in isolation.

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?

States a specific verb and resource ("Key event counts from Google Analytics") plus the two possible breakdown grains and the optional period comparison. An agent can tell it reports key-event metrics rather than, say, landing pages or traffic acquisition. It stops short of naming a sibling it resembles most (e.g. ecommerce performance for purchase events), so it does not fully differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Organic Search by default" implies when this returns organic-scoped data and signals that channel must be widened for all traffic, which is useful implied guidance. However, there is no explicit when-to-use versus alternatives, no when-not-to-use, and no prerequisites beyond what the schema states for projectId.

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