Skip to main content
Glama
sudomichael

Gizmo Analytics

get_top_pages

Read-onlyIdempotent

Retrieve top page paths by event count. Filter by dimensions like country, device, or date range to analyze specific segments.

Instructions

Top page paths by event count. Supports filters (e.g. country=US) so you can answer "top pages from Germany." Pass site_id to scope to one site.

Optional dimension filters. Each filter is {dim, op, value}. Available dims: page, entry_page, exit_page, referrer, hostname, channel, ai_source, utm_source, utm_medium, utm_campaign, country, region, city, language, device, browser, screen, event_name, or prop:. Available ops: is, is_not, contains, not_contains. Filters AND together. Example: [{dim:'country', op:'is', value:'US'}, {dim:'device', op:'is_not', value:'mobile'}].

Optional date range. Either {preset:'last_7_days'} (also: today, yesterday, last_14_days, last_30_days, last_90_days, last_year, month_to_date, last_month, all_time) OR {from:'2026-05-01', to:'2026-05-15'} for a custom range (ISO 8601 dates or timestamps). Defaults vary by tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
site_idNoInternal site UUID. Get one from list_sites. Omit to scope to the entire workspace.
date_rangeNoOptional date range. Either {preset:'last_7_days'} OR {from:'2026-05-01', to:'2026-05-15'}. Defaults per tool — usually last_7_days.
filtersNoAND-joined dimension filters.
limitNoMax number of rows to return. Defaults to 20, capped at 200. Pagination via date_range for larger windows.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsYesTop-N rows sorted by visitor count, descending.
Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds context about the return data (top pages by count) and filtering capabilities. No contradictions; behavior is consistent with a safe, read-only query.

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 description is informative but somewhat verbose, with multiple sentences listing dimensions and operators. It could be more streamlined while retaining clarity. Front-loaded with the main purpose.

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?

Given the existence of an output schema, the description does not need to explain return values. It covers all necessary aspects: what it returns, filtering, date range, and scoping. Complete for a query tool with rich annotations.

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 baseline is 3. The description adds value by providing examples of filter usage and listing available dimensions, including custom properties (prop:<name>), which goes beyond the schema descriptions.

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 explicitly states 'Top page paths by event count' with a clear verb and resource. It distinguishes itself from siblings like get_top_referrers and get_breakdown by focusing on page paths.

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?

The description provides context on when to use filters and site_id scoping, with a concrete example ('top pages from Germany'). It does not explicitly state when not to use it or name direct alternatives, but the usage is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sudomichael/gizmoanalytics-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server