Skip to main content
Glama
Sign In

Privatrak

by com.privatrak
OverviewDiscussionsAdmin

Page views per page

list_pages
Read-onlyIdempotent

Pages by views, paged; search; sort_by views, entries, time_on_page, scroll_depth, page. A page is origin + path (no query/anchor). views: pageview events, not visitors. entries: visitors landing there, from entries_from. avg_time_on_page_seconds, avg_scroll_depth (% down): mean of views reporting one; null: none. avg_scroll_depth_change is in points. Null average change: engagement_change_unavailable, else no previous value. Dates are the project's calendar days, YYYY-MM-DD (timezone: get_project); timestamps are UTC. Omit from/to for the last 28 complete days, ending yesterday. Today is still in progress: a range including it reads as a drop against complete days. A period marked starts_before_data begins before the project has data (see data_from): those days read as zero, not as a quiet period. Quote counts with every percentage; a big change on a small count is noise, not a finding.

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": "list_pages"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLast day, YYYY-MM-DD in the project's timezone, inclusive. Default: yesterday, the last complete day.
fromNoFirst day, YYYY-MM-DD in the project's timezone, inclusive. Default: 27 days before 'to'.
pageNoPage number, from 1.
limitNoPages per page, 1-100. Default 50.
traitNoOnly count page views by visitors carrying this session trait value.
searchNoCase-insensitive substring of the page's origin followed by its path, e.g. pricing or app.example.com/settings.
projectNoProject ID, from list_projects. Required when this connection covers more than one project; may be left out when it covers one (and with an API key, which belongs to one project).
sort_byNoviews (default), entries (visitors who landed on the page), time_on_page, scroll_depth (the averages; pages without one last) or page (origin, then path).
sort_dirNoasc or desc. Default: desc for views, entries, time_on_page and scroll_depth, asc for page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / sort_by / description
      Previous value: -"views (default), entries (visitors who landed on the page) or page (origin, then path)."New value: +"views (default), entries (visitors who landed on the page), time_on_page, scroll_depth (the averages; pages without one last) or page (origin, then path)."
    • changedInput schema / properties / sort_dir / description
      Previous value: -"asc or desc. Default: desc for views and entries, asc for page."New value: +"asc or desc. Default: desc for views, entries, time_on_page and scroll_depth, asc for page."
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnly/idempotent/closed-world; the description adds genuinely behavioral context the agent could not infer: default 28-day window ending yesterday, today-in-progress distortion, pre-`data_from` days reading as zero rather than quiet, and null semantics for averages. The remaining gap is return shape and pagination limits in practice.

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?

Front-loaded and information-dense with no filler sentences, but the opening is telegraphic ("Pages by views, paged; search; sort_by ...") and the body is semicolon-chained fragments rather than cleanly structured clauses. Every fact earns its place, yet scanning it costs more than it should.

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 9-parameter analytics listing with no output schema, the description covers defaults, timezone rules, metric definitions, null handling and data-boundary caveats. It stops short of describing the returned record fields (page, views, entries, averages, change) or page-size behaviour, which is the main residual gap.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: views counts pageview events rather than visitors, entries comes from entries_from, avg_scroll_depth is percent down and its change is in points, and a null change means engagement_change_unavailable. These definitions materially change how the returned numbers should be read.

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?

"Pages by views, paged" states a specific resource (pages) and the ranking dimension (views), and the definition of a page as origin + path pins down the unit of aggregation. It does not name a sibling to contrast with (e.g. get_overview for aggregate traffic), so an agent must infer the granularity difference.

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?

The description gives useful operating context — omit from/to for the last 28 complete days, don't include today because it reads as a drop, watch starts_before_data — but these are interpretation rules rather than when-to-use-this-vs-alternatives guidance. Nothing tells the agent when to prefer get_overview, list_sources, or run_insights_query instead.

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

All Privatrak toolsInspect
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.

Resources