Skip to main content
Glama

Read an app's analytics

get_app_analytics
Read-only

Reads event analytics as aggregate totals, distinct actors, daily counts, N+ repeats, property breakdowns, and 1/7/30 retention, helping answer signup and return-rate questions without a dashboard.

Instructions

Reads the product events a workspace's app records with analytics.track — as aggregates only: totals and distinct actors per event, per-day counts, actors who did something N+ times, counts by a property value, and retention cohorts (day 1/7/30). Never a list of who did what. The request has the same shape as analytics.report() in a block. Use it to answer 'how many people arrived / signed up / came back after 7 days' without writing a dashboard first.

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": {
      "workspaceId": "<workspaceId>"
    },
    "name": "get_app_analytics"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoWindow in days (default 30).
dailyNo
eventsNo
atLeastNo
retentionNo
breakdownsNo
workspaceIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.3/5.0
Behavior4/5

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

The readOnlyHint annotation already covers the safety profile, and the description adds substantive behavior beyond it: results are aggregates only, computed across five distinct reporting modes, and the request mirrors analytics.report() in a block. With no output schema, the return-shape disclosure (totals, distinct actors, per-day counts, cohorts) is doing real work; only permissions and any cost/latency characteristics go unmentioned.

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 sentences, front-loaded with the aggregate-only constraint and the enumeration of report types, ending with a concrete use-case that anchors intent. The middle sentence is a dense list but every element corresponds to a schema parameter, so little is wasted; the analytics.report() analogy could have been folded in more tightly.

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 7-parameter read tool with nested objects and no output schema, the description supplies the return semantics, the request shape, and a usage example — enough for an agent to call it correctly. Missing pieces are minor: default/unbounded behavior when events or days are omitted, and the meaning of workspaceId are left to the schema.

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 only 14% with 7 parameters and nested retention/atLeast/breakdowns objects, so the description carries most of the semantic load — and it does, mapping nearly every request option to what it computes (events→totals/distinct actors, daily→per-day counts, atLeast→N+ times, breakdowns→counts by property value, retention→day 1/7/30 cohorts). It does not clarify workspaceId or the retention.cohort/activity sub-fields, so a small gap remains.

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 names a specific verb and resource — 'Reads the product events a workspace's app records with analytics.track' — and immediately narrows it to 'aggregates only', explicitly ruling out a raw event list ('Never a list of who did what'). That contrast is a real differentiation from list/traffic style siblings such as get_site_visitors, letting an agent pick this tool without opening its schema.

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 when-to-use framing: answer 'how many people arrived / signed up / came back after 7 days' without building a dashboard first, plus an implicit exclusion of row-level questions. It stops short of naming an alternative tool for when the agent does need per-actor detail, so it is strong context rather than a full when/when-not/alternative map.

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