Skip to main content
Glama

Analytics

analytics
Read-only

Run any report on the site's traffic: overview, realtime, channels, ai_search, sources, landing_pages, pages, shipped_work, ai_crawlers, conversions, errors, timeseries, funnels, page_flow, users, user. AI Search is its own channel, broken out per engine, and shipped work is a dimension. users: the people the product's own server reports (POST /t/u, routines/users.md): signups, activation (the users_activation rule), active and paying people, weekly cohorts, and each person with what they did and where they came from; user (with user): one person's timeline. Default period: the last 28 days. 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": {
      "report": "<report>"
    },
    "name": "analytics"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoYYYY-MM-DD
fromNoYYYY-MM-DD
userNouser report only: the product's own id for the person
limitNo
metricNotimeseries only
reportYes
siteIdNo
compareNoAlso the previous period of the same length
filtersNo
intervalNotimeseries only

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / report / enum
      Previous value: -[
      -  "overview",
      -  "realtime",
      -  "channels",
      -  "ai_search",
      -  "sources",
      -  "landing_pages",
      -  "pages",
      -  "shipped_work",
      -  "ai_crawlers",
      -  "conversions",
      -  "errors",
      -  "timeseries",
      -  "funnels",
      -  "page_flow"
      -]New value: +[
      +  "overview",
      +  "realtime",
      +  "channels",
      +  "ai_search",
      +  "sources",
      +  "landing_pages",
      +  "pages",
      +  "shipped_work",
      +  "ai_crawlers",
      +  "conversions",
      +  "errors",
      +  "timeseries",
      +  "funnels",
      +  "page_flow",
      +  "users",
      +  "user"
      +]
    • addedInput schema / properties / user
      Added value: +{
      +  "description": "user report only: the product's own id for the person",
      +  "maxLength": 128,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / report / enum
      Previous value: -[
      -  "overview",
      -  "realtime",
      -  "channels",
      -  "ai_search",
      -  "sources",
      -  "landing_pages",
      -  "pages",
      -  "shipped_work",
      -  "ai_crawlers",
      -  "conversions",
      -  "errors",
      -  "timeseries"
      -]New value: +[
      +  "overview",
      +  "realtime",
      +  "channels",
      +  "ai_search",
      +  "sources",
      +  "landing_pages",
      +  "pages",
      +  "shipped_work",
      +  "ai_crawlers",
      +  "conversions",
      +  "errors",
      +  "timeseries",
      +  "funnels",
      +  "page_flow"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / report / enum
      Previous value: -[
      -  "overview",
      -  "realtime",
      -  "channels",
      -  "ai_search",
      -  "sources",
      -  "landing_pages",
      -  "pages",
      -  "shipped_work",
      -  "ai_crawlers",
      -  "conversions",
      -  "timeseries"
      -]New value: +[
      +  "overview",
      +  "realtime",
      +  "channels",
      +  "ai_search",
      +  "sources",
      +  "landing_pages",
      +  "pages",
      +  "shipped_work",
      +  "ai_crawlers",
      +  "conversions",
      +  "errors",
      +  "timeseries"
      +]
  4. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish read-only, non-destructive, non-open-world behavior, and the description adds real context beyond them: the 28-day default window, the zero-cost call, that AI Search is broken out per engine, and that `users` data comes from the product's own server (POST /t/u). It does not say how much data a call returns or any pagination/row-cap behavior, which is a gap for a reporting tool.

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 report enumeration is correctly front-loaded, but the second half is a run-on that buries the `users` vs `user` distinction in a long clause, and the parenthetical "(POST /t/u, routines/users.md)" is internal implementation detail that consumes attention without helping a caller. Tightening would materially improve scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With sixteen report variants, ten parameters, and no output schema, the description should do more than enumerate names — an agent still cannot tell what shape each report returns or which fields `filters` accepts. Defaults, cost, and the two-variant disambiguation are covered, but the return-side and filter-field gaps are significant for a tool of this complexity.

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 60%, and the description covers some of the remainder well — it maps `user` to the `user` report and explains what the `users` dimension measures. But `filters`, `limit`, `siteId`, and `compare` get no meaning beyond the schema, and the `report` enum itself carries no description in the schema, so field-name semantics for filtering are left unexplained.

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?

Opens with a specific verb+resource ("Run any report on the site's traffic") and then enumerates all sixteen valid report values, so an agent knows exactly what this tool covers. The per-report clauses for `users` and `user` disambiguate the two similar-sounding variants, and nothing overlaps a sibling's stated purpose.

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?

Gives concrete selection context for the ambiguous cases — `users` is the cohort/people report while `user` requires the `user` argument and returns one person's timeline — plus the default period and that the call is free. It stops short of naming when to prefer a sibling such as `visibility`, `today`, or `funnel_check` for overlapping questions.

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