Skip to main content
Glama

Get audience statistics

get_audience_stats
Read-onlyIdempotent

Use this when the founder asks how many signups they have, how a week or a launch is going, how many verified their email, where signups come from, or how well the launch page converts. Not for finding or listing people (use search_audience), for the top referrers (use get_leaderboard), or for the plan's billable contact count (use get_workspace).

It returns total audience, signups today and over a trailing window, how many verified their email (confirmed: they clicked the link we sent to verify their address; everyone who joins is subscribed either way), and the breakdown by subscription status, pipeline stage and first-touch source.

Every number comes from precomputed counters, so it costs a handful of indexed row reads no matter how large the audience is. To count, use this rather than paging through search_audience: that is capped at 50 rows per call and wrong as soon as there is a second page.

total counts live contacts and excludes test-mode and flagged-for-review rows, so it can differ from the billable count in get_workspace. referred counts signups that arrived through somebody's referral link.

views is how many times the launch page was viewed over the same window, and conversion is the percentage of those visits that became signups on that page (page_signups, the numerator: signups from an import, the API or an embed have no visit behind them and are not counted). It is null, with conversion_note, when there were no views or more signups than views.

The plan sets limits, the same ones the Analytics page has. days is capped at how far back the plan's analytics history reaches: a longer request is shortened, and signups.window_days is the window actually used. source is null unless the plan includes advanced analytics. total counts every saved contact, including any held past the plan's size; hidden_contacts is how many of those the founder cannot see or use until the plan holds them.

When the plan limits any of that, the answer is still returned, with a reason beside the missing part (source_unavailable_reason, window_limited_reason, hidden_contacts_reason) and one upgrade object: the lowest plan that clears all of them, with its link. Say plainly what is missing and why it matters for what the founder asked, and give them the link. Do not mention an upgrade when there is no upgrade object.

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": {
      "project": "<project>"
    },
    "name": "get_audience_stats"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoHow many days of daily arrivals to include, counting back from today. 1-90, defaults to 7.
projectYesThe project handle, like `prj_…`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavior the annotations cannot express: results come from precomputed counters so cost stays flat regardless of audience size, `days` is silently shortened to the plan's history, `source` is null without advanced analytics, `conversion` is null with a note when views are zero or fewer than signups, and `total` excludes test-mode and review-flagged rows so it differs from the billable count. It also states the failure-mode contract: partial results still return with reason fields plus an `upgrade` object, and no upgrade should be mentioned when that object is absent.

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

Conciseness4/5

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

Usage routing is front-loaded in the first paragraph and the distinctions from siblings come before any return-value detail, which is the right order. It is long — eight paragraphs — and the `referred` definition and the precomputed-counter justification could be folded into the surrounding sentences, but nearly every sentence carries information an agent would otherwise have to guess.

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?

With no output schema, the description carries the full burden of explaining the return shape, and it does: it names the fields (`confirmed`, `total`, `referred`, `views`, `conversion`, `page_signups`, `hidden_contacts`, `window_days`), the reason fields and the `upgrade` object that accompany plan-limited results. Nothing an agent needs to call this correctly or to interpret a degraded response is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents `days` as 1-90 default 7 and `project` as a `prj_…` handle, yet the description adds real meaning: a longer `days` request is truncated to the plan's analytics history and `signups.window_days` reports the window actually used. That is a behavioral contract for the parameter the schema does not convey, since the schema advertises a 90 maximum that the plan may override.

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 opens with concrete founder questions (signups, verified emails, where signups come from, launch conversion) and then enumerates exactly what is returned: total audience, signups today and over a trailing window, confirmed count, and breakdowns by subscription status, pipeline stage and first-touch source. It explicitly carves itself away from `search_audience`, `get_leaderboard` and `get_workspace`, so an agent can identify it without opening a 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?

It gives both sides: use it when the founder asks a counting/trending/conversion question, and do not use it for listing people, top referrers, or billable contact counts, naming the replacement tool for each. It goes further by saying to use this rather than paging `search_audience` for counts and explaining why (50-row cap makes paging wrong past the first page).

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.