Skip to main content
Glama
flowsery

flowsery

Official

Get Visitors by Device

get_devices
Read-onlyIdempotent

Retrieve visitor counts split by Desktop, Mobile, and Tablet for a date range to compare mobile versus desktop traffic.

Instructions

Get visitors split by device type (Desktop, Mobile, Tablet), ranked by visitors descending, for a date range. Use this for the mobile-versus-desktop question; use get_browsers or get_operating_systems for the software split. Pass filter_device to any other tool to restrict it to one device type instead. Three rows at most, so pagination rarely matters. Rows carry value, visitors, revenue, and percentage. Dates default to the last 30 days; all filter_* arguments apply. Requires websiteId or domain with a workspace token.

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": "get_devices"
  }
}

Input Schema

NameRequiredDescriptionDefault
endAtNoISO 8601 end of the reporting window (e.g. "2026-01-31"). Defaults to now.
limitNoPage size: how many of the top rows to return in this call. Omit for 100. Raise it for long-tail lists such as cities or pages.
domainNoWebsite domain from list_websites (e.g. "example.com"). Alternative to websiteId with a workspace token.
offsetNoHow many top rows to skip, for reading the next page. Omit to start at the first row. Keep paging while offset + limit is below pagination.total in the response.
startAtNoISO 8601 start of the reporting window, date or datetime (e.g. "2026-01-01" or "2026-01-01T00:00:00Z"). Defaults to 30 days ago.
timezoneNoIANA timezone used to bound and bucket the window (e.g. "America/New_York"). Defaults to the website timezone from get_metadata.
filter_osNoFilter by operating system name as returned by get_operating_systems (e.g. "iOS")
websiteIdNoWebsite ID from list_websites. Required with a workspace token unless domain is given; ignored with a website key.
filter_refNoKeep only visitors whose first visit landed on a URL carrying this ?ref= tag, e.g. "producthunt" for example.com/?ref=producthunt. Values appear in get_breakdown with dimension ref.
filter_viaNoKeep only sessions that landed on a URL carrying this ?via= tag, e.g. "jane" for example.com/?via=jane, the form many affiliate and referral programs use. Matched per session, not per visitor. Values appear in get_breakdown with dimension via.
filter_cityNoFilter by city name as returned by get_cities
filter_goalNoKeep only visitors who completed this goal in the window, e.g. "newsletter_signup". Goal names appear in get_goals.
filter_pageNoKeep only sessions that viewed this page path at least once, e.g. "/pricing". Paths appear in get_pages.
workspaceIdNoWorkspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another
filter_deviceNoFilter by device type as returned by get_devices: "Desktop", "Mobile" or "Tablet". Matching is case-sensitive.
filter_regionNoFilter by region name as returned by get_regions (e.g. "California")
filter_sourceNoKeep only visitors whose first visit landed on a URL carrying this ?source= tag, e.g. "twitter" for example.com/?source=twitter. Values appear in get_breakdown with dimension source.
filter_browserNoFilter by browser name as returned by get_browsers (e.g. "Chrome")
filter_channelNoKeep only visitors whose first visit came from this marketing channel, e.g. "Organic Search" or "Paid Social". Channel names appear in get_channels.
filter_countryNoFilter by country name as returned by get_countries (e.g. "United States"). Every filter_* value accepts the same operators: "v" is, "!v" is not, "~v" contains, "!~v" does not contain, "a|b" any of. Filters combine with AND.
filter_hostnameNoKeep only sessions with at least one pageview on this hostname, e.g. "app.example.com" when one website tracks several domains or subdomains. Hostnames appear in get_hostnames.
filter_referrerNoFilter by referrer as returned by get_referrers: a source name such as "Google" for recognized sites, otherwise the domain
filter_utm_termNoKeep only visitors whose first visit was tagged with this utm_term, usually the paid search keyword, e.g. "web analytics". Values appear in get_breakdown with dimension utm_term.
filter_entry_pageNoKeep only visitors whose first visit started on this page path, their landing page, e.g. "/blog/launch". Paths appear in get_breakdown with dimension entry_page.
filter_utm_mediumNoKeep only visitors whose first visit was tagged with this utm_medium, the kind of marketing, e.g. "email", "cpc" or "social". Values appear in get_breakdown with dimension utm_medium.
filter_utm_sourceNoKeep only visitors whose first visit was tagged with this utm_source, the sender of the traffic, e.g. "newsletter" or "google". Values appear in get_breakdown with dimension utm_source.
filter_utm_contentNoKeep only visitors whose first visit was tagged with this utm_content, which tells apart ads or links in one campaign, e.g. "header_cta". Values appear in get_breakdown with dimension utm_content.
filter_utm_campaignNoKeep only visitors whose first visit was tagged with this utm_campaign, the campaign name, e.g. "black_friday". Values appear in get_campaigns.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed32 schema fields changedv1.5.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / filter_channel / description
      Previous value: -"Filter by marketing channel as returned by get_channels (e.g. \"Organic Search\")"New value: +"Keep only visitors whose first visit came from this marketing channel, e.g. \"Organic Search\" or \"Paid Social\". Channel names appear in get_channels."
    • changedInput schema / properties / filter_device / description
      Previous value: -"Filter by device type: desktop, mobile, tablet"New value: +"Filter by device type as returned by get_devices: \"Desktop\", \"Mobile\" or \"Tablet\". Matching is case-sensitive."
    • changedInput schema / properties / filter_entry_page / description
      Previous value: -"Filter by entry/landing page"New value: +"Keep only visitors whose first visit started on this page path, their landing page, e.g. \"/blog/launch\". Paths appear in get_breakdown with dimension entry_page."
    • changedInput schema / properties / filter_goal / description
      Previous value: -"Filter to visitors who completed this goal name (as returned by get_goals)"New value: +"Keep only visitors who completed this goal in the window, e.g. \"newsletter_signup\". Goal names appear in get_goals."
    • changedInput schema / properties / filter_hostname / description
      Previous value: -"Filter by hostname as returned by get_hostnames (e.g. \"app.example.com\")"New value: +"Keep only sessions with at least one pageview on this hostname, e.g. \"app.example.com\" when one website tracks several domains or subdomains. Hostnames appear in get_hostnames."
    • changedInput schema / properties / filter_page / description
      Previous value: -"Filter by page path as returned by get_pages (e.g. \"/pricing\")"New value: +"Keep only sessions that viewed this page path at least once, e.g. \"/pricing\". Paths appear in get_pages."
    • changedInput schema / properties / filter_ref / description
      Previous value: -"Filter by ref URL parameter"New value: +"Keep only visitors whose first visit landed on a URL carrying this ?ref= tag, e.g. \"producthunt\" for example.com/?ref=producthunt. Values appear in get_breakdown with dimension ref."
    • changedInput schema / properties / filter_referrer / description
      Previous value: -"Filter by referrer domain as returned by get_referrers (e.g. \"google.com\")"New value: +"Filter by referrer as returned by get_referrers: a source name such as \"Google\" for recognized sites, otherwise the domain"
    • changedInput schema / properties / filter_region / description
      Previous value: -"Filter by region code as returned by get_regions (e.g. US-CA)"New value: +"Filter by region name as returned by get_regions (e.g. \"California\")"
    • changedInput schema / properties / filter_source / description
      Previous value: -"Filter by source URL parameter"New value: +"Keep only visitors whose first visit landed on a URL carrying this ?source= tag, e.g. \"twitter\" for example.com/?source=twitter. Values appear in get_breakdown with dimension source."
    • changedInput schema / properties / filter_utm_campaign / description
      Previous value: -"Filter by UTM campaign"New value: +"Keep only visitors whose first visit was tagged with this utm_campaign, the campaign name, e.g. \"black_friday\". Values appear in get_campaigns."
    • changedInput schema / properties / filter_utm_content / description
      Previous value: -"Filter by UTM content"New value: +"Keep only visitors whose first visit was tagged with this utm_content, which tells apart ads or links in one campaign, e.g. \"header_cta\". Values appear in get_breakdown with dimension utm_content."
    • changedInput schema / properties / filter_utm_medium / description
      Previous value: -"Filter by UTM medium"New value: +"Keep only visitors whose first visit was tagged with this utm_medium, the kind of marketing, e.g. \"email\", \"cpc\" or \"social\". Values appear in get_breakdown with dimension utm_medium."
    • changedInput schema / properties / filter_utm_source / description
      Previous value: -"Filter by UTM source"New value: +"Keep only visitors whose first visit was tagged with this utm_source, the sender of the traffic, e.g. \"newsletter\" or \"google\". Values appear in get_breakdown with dimension utm_source."
    • changedInput schema / properties / filter_utm_term / description
      Previous value: -"Filter by UTM term"New value: +"Keep only visitors whose first visit was tagged with this utm_term, usually the paid search keyword, e.g. \"web analytics\". Values appear in get_breakdown with dimension utm_term."
    • changedInput schema / properties / filter_via / description
      Previous value: -"Filter by via URL parameter"New value: +"Keep only sessions that landed on a URL carrying this ?via= tag, e.g. \"jane\" for example.com/?via=jane, the form many affiliate and referral programs use. Matched per session, not per visitor. Values appear in get_breakdown with dimension via."
    • changedInput schema / properties / limit / description
      Previous value: -"Max rows to return (1-1000, default 100)."New value: +"Page size: how many of the top rows to return in this call. Omit for 100. Raise it for long-tail lists such as cities or pages."
    • addedInput schema / properties / limit / maximum
      Added value: +1000
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • changedInput schema / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • changedInput schema / properties / offset / description
      Previous value: -"Rows to skip for pagination (default 0). Compare offset + limit against pagination.total in the response."New value: +"How many top rows to skip, for reading the next page. Omit to start at the first row. Keep paging while offset + limit is below pagination.total in the response."
    • addedInput schema / properties / offset / minimum
      Added value: +0
    • changedInput schema / properties / offset / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / workspaceId
      Added value: +{
      +  "description": "Workspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another",
      +  "type": "string"
      +}
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedOutput schema / properties / result / additionalProperties
      Added value: +true
    • removedOutput schema / properties / result / description
      Removed value: -"Object with status, data (up to three rows, desktop, mobile, tablet, with value, visitors, revenue, percentage), and pagination."
    • addedOutput schema / properties / result / properties
      Added value: +{
      +  "data": {
      +    "items": {
      +      "additionalProperties": true,
      +      "properties": {
      +        "countryCode": {
      +          "description": "ISO 3166-1 alpha-2, on geographic rows",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "iconUrl": {
      +          "$ref": "#/properties/result/properties/data/items/properties/countryCode",
      +          "description": "Favicon of the referring site, on referrer rows"
      +        },
      +        "newRevenue": {
      +          "$ref": "#/properties/result/properties/data/items/properties/revenue"
      +        },
      +        "percentage": {
      +          "$ref": "#/properties/result/properties/data/items/properties/revenue",
      +          "description": "This row's share of visitors in the window, 0-100"
      +        },
      +        "renewalRevenue": {
      +          "$ref": "#/properties/result/properties/data/items/properties/revenue"
      +        },
      +        "revenue": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "value": {
      +          "description": "The dimension value, such as a page path, referrer or country name. \"Unknown\" when it was not captured",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "visitors": {
      +          "type": "number"
      +        }
      +      },
      +      "required": [
      +        "value",
      +        "visitors"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "pagination": {
      +    "additionalProperties": true,
      +    "properties": {
      +      "limit": {
      +        "type": "number"
      +      },
      +      "offset": {
      +        "type": "number"
      +      },
      +      "total": {
      +        "description": "Rows matching the query before paging",
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "limit",
      +      "offset",
      +      "total"
      +    ],
      +    "type": "object"
      +  },
      +  "status": {
      +    "description": "\"success\" on every successful call",
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / properties / result / required
      Added value: +[
      +  "status",
      +  "data",
      +  "pagination"
      +]
    • addedOutput schema / properties / result / type
      Added value: +"object"
    • addedOutput schema / required
      Added value: +[
      +  "result"
      +]
  2. Changed18 schema fields changedv0.1.1
    • changedInput schema / properties / domain / description
      Previous value: -"Website domain to query. Required when using a workspace token unless websiteId is provided."New value: +"Website domain from list_websites (e.g. \"example.com\"). Alternative to websiteId with a workspace token."
    • changedInput schema / properties / endAt / description
      Previous value: -"ISO 8601 end date (e.g. \"2026-01-31\")"New value: +"ISO 8601 end of the reporting window (e.g. \"2026-01-31\"). Defaults to now."
    • changedInput schema / properties / filter_browser / description
      Previous value: -"Filter by browser name"New value: +"Filter by browser name as returned by get_browsers (e.g. \"Chrome\")"
    • changedInput schema / properties / filter_channel / description
      Previous value: -"Filter by marketing channel"New value: +"Filter by marketing channel as returned by get_channels (e.g. \"Organic Search\")"
    • changedInput schema / properties / filter_city / description
      Previous value: -"Filter by city"New value: +"Filter by city name as returned by get_cities"
    • changedInput schema / properties / filter_country / description
      Previous value: -"Filter by country"New value: +"Filter by country name as returned by get_countries (e.g. \"United States\"). Every filter_* value accepts the same operators: \"v\" is, \"!v\" is not, \"~v\" contains, \"!~v\" does not contain, \"a|b\" any of. Filters combine with AND."
    • changedInput schema / properties / filter_goal / description
      Previous value: -"Filter by goal name"New value: +"Filter to visitors who completed this goal name (as returned by get_goals)"
    • changedInput schema / properties / filter_hostname / description
      Previous value: -"Filter by hostname"New value: +"Filter by hostname as returned by get_hostnames (e.g. \"app.example.com\")"
    • changedInput schema / properties / filter_os / description
      Previous value: -"Filter by operating system"New value: +"Filter by operating system name as returned by get_operating_systems (e.g. \"iOS\")"
    • changedInput schema / properties / filter_page / description
      Previous value: -"Filter by page path"New value: +"Filter by page path as returned by get_pages (e.g. \"/pricing\")"
    • changedInput schema / properties / filter_referrer / description
      Previous value: -"Filter by referrer domain"New value: +"Filter by referrer domain as returned by get_referrers (e.g. \"google.com\")"
    • changedInput schema / properties / filter_region / description
      Previous value: -"Filter by region"New value: +"Filter by region code as returned by get_regions (e.g. US-CA)"
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (1-1000, default: 100)"New value: +"Max rows to return (1-1000, default 100)."
    • changedInput schema / properties / offset / description
      Previous value: -"Pagination offset (default: 0)"New value: +"Rows to skip for pagination (default 0). Compare offset + limit against pagination.total in the response."
    • changedInput schema / properties / startAt / description
      Previous value: -"ISO 8601 start date (e.g. \"2026-01-01\")"New value: +"ISO 8601 start of the reporting window, date or datetime (e.g. \"2026-01-01\" or \"2026-01-01T00:00:00Z\"). Defaults to 30 days ago."
    • changedInput schema / properties / timezone / description
      Previous value: -"IANA timezone (e.g. \"America/New_York\"). Falls back to site default."New value: +"IANA timezone used to bound and bucket the window (e.g. \"America/New_York\"). Defaults to the website timezone from get_metadata."
    • changedInput schema / properties / websiteId / description
      Previous value: -"Website ID to query. Required when using a workspace token unless domain is provided."New value: +"Website ID from list_websites. Required with a workspace token unless domain is given; ignored with a website key."
    • changedOutput schema / properties / result / description
      Previous value: -"Device types (desktop, mobile, tablet) with visitor counts."New value: +"Object with status, data (up to three rows, desktop, mobile, tablet, with value, visitors, revenue, percentage), and pagination."
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent, closed read, so the bar is lower, yet the description still adds substantial context: the result is capped at three rows so pagination rarely matters, the default window is the last 30 days, all filter_* arguments apply, and it requires websiteId or domain with a workspace token. That auth prerequisite in particular is the kind of operational detail annotations cannot convey.

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?

The purpose and the device-versus-software distinction are front-loaded, and each subsequent sentence carries distinct information: the routing tip, the row cap, the returned fields, the default window, and the auth requirement. Nothing is repeated and nothing reads as padding.

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 tool with 28 largely optional parameters it covers the essentials: auth prerequisite, default window, output shape, and why pagination is unimportant here. With a 100%-covered schema and an output schema present, the remaining per-parameter detail is rightly delegated rather than repeated.

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 100%, so every one of the 28 parameters is already documented in the input schema, establishing the baseline of 3. The description notes that dates default to 30 days and that all filter_* arguments apply, but it does not add syntax or operator detail beyond what the schema already provides for individual filters.

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?

States a specific verb and resource ('Get visitors split by device type'), enumerates the three values, and names the sort order. It explicitly differentiates itself from get_browsers and get_operating_systems, so an agent can route between the device and software breakdowns without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete when-to-use trigger ('the mobile-versus-desktop question'), names the sibling alternatives for a different split, and offers a contrasting approach (pass filter_device to any other tool) for the single-device case. Both the alternative and the condition that selects it are stated.

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