Skip to main content
Glama

Sextant Web - Website GEO, SEO, and Analytics

Get website retention

analytics_getWebsiteRetention
Read-onlyIdempotent

Returning visitors: for each first-visit day in the range, how many came back on each later day, as counts and percentages. Dates: leave them out for the app's Last 7 days (today and the 6 days before it, from midnight in the site's time zone), or pass range (the app's presets), or startDate and endDate as days (YYYY-MM-DD, both included). timezone defaults to the site's. It calls one fixed endpoint of the Sextant Analytics API (https://sextantweb.com/docs/ai): path filters page URLs, query filters page query strings.

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": {
      "siteId": "<siteId>"
    },
    "name": "analytics_getWebsiteRetention"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNoOperating system used by the visitor.
tagNoTag attached to the tracked activity.
cityNoCity of the visitor.
pathNoFilter by page URL path.
unitNoTime interval used to group results: minute, hour, day, month, or year.
endAtNoEnd of the date range as a Unix timestamp in milliseconds.
eventNoFilter by custom event name.
matchNoWhether records must match all filters or any filter.
queryNoFilter by page URL query string.
rangeNoA preset from the app's date picker, in the site's time zone. 7d, 30d, 90d: today and the days before it, from local midnight. 24h: the current hour and the 23 before it. 12m, 24m, 36m: this month and the months before it, from the 1st. month: this month. today: since local midnight. It gives the same numbers as the app. Leave out the other date fields when you use it.
titleNoFilter by page title.
cohortNoID of a saved cohort used to filter visitors.
deviceNoDevice category used by the visitor.
regionNoRegion or subdivision of the visitor.
siteIdYesThe Sextant site ID.
browserNoBrowser used by the visitor.
countryNoCountry code of the visitor.
endDateNoLast day of the range (YYYY-MM-DD), included to its end in the site's time zone. An ISO date-time is used as is.
segmentNoID of a saved segment used to filter results.
startAtNoStart of the date range as a Unix timestamp in milliseconds.
utmTermNoUTM campaign search term.
hostnameNoHostname on which the activity occurred.
languageNoPreferred language reported by the visitor browser.
objectIdNoOptional: a short link or tracking pixel of this site, to read its analytics instead of the site's.
referrerNoFilter by referring URL.
timezoneNoIANA time zone used to interpret dates and group results, for example America/New_York.
eventTypeNoEvent type: 1 for a pageview or 2 for a custom event.
startDateNoFirst day of the range (YYYY-MM-DD), from local midnight in the site's time zone. An ISO date-time is used as is.
utmMediumNoUTM campaign medium.
utmSourceNoUTM campaign source.
distinctIdNoCustom identifier assigned to the visitor.
utmContentNoUTM campaign content.
utmCampaignNoUTM campaign name.
excludeBounceNoSet a non-empty value to exclude visits with only one pageview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavior beyond that: the default date window and its timezone anchoring, that `timezone` falls back to the site's zone, and that it hits one fixed endpoint (with a docs URL). It omits any statement about result volume, pagination, or ordering, so it is not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what the tool returns, then the date-handling rules, then the endpoint note — the most decision-relevant material comes first. No filler sentences; every clause carries either output semantics, date semantics, or filter disambiguation.

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 34 parameters, no output schema, and only one required field, the description carries the burden of explaining the return value, and it does so concretely (per-first-visit-day return counts and percentages). Date conflict resolution and timezone defaults are covered. Remaining gaps are pagination/limits and the semantics of the cohort/segment filters, which are left entirely 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 100%, so 3 is the baseline, but the description earns more: it resolves the ambiguity between the mutually exclusive date inputs ('leave them out… or pass range… or startDate and endDate'), pins the default range and timezone, and disambiguates `path` (URL path) from `query` (URL query string), which the schema's near-identical wording leaves blurry. It does not touch the other ~30 filter params, which the schema already documents.

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?

The opening clause defines the exact output shape with a specific verb-like framing: 'for each first-visit day in the range, how many came back on each later day, as counts and percentages.' That is unmistakably a retention/cohort-return report, clearly distinct from sibling metrics, breakdown, or funnel tools. It stops short of naming a sibling or stating an exclusion, which keeps it at 4 rather than 5.

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?

It gives operational guidance on the date arguments: omit them for the app's Last 7 days (today minus 6, from local midnight), or pass `range` presets, or `startDate`/`endDate`, plus the default timezone. What it never states is when to pick this tool over analytics_getWebsiteBreakdown or analytics_getWebsiteMetrics — the reader must infer that from the retention framing. Useful context, but not true use-vs-alternative guidance.

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