Skip to main content
Glama

One part of an app's numbers

app_topic
Read-only

One topic for one app: numbers (key numbers: downloads, people, new people, money, sales, who pays, rating); highlights (sales, best days, milestones, new countries, releases, reviews, new problems, ads starting and stopping); countries (downloads by country, iPhone and Android); sources (where people found the app: store sources, recorded install sources, money by source); buyers (who bought, how soon after installing, what they did first, where they came from); problems (crashes and errors the app caught, failures it reported, Google Play crash counts); versions (which version people use, per platform); visits (a few recent visits, step by step, with the Mixpanel session replay id when the app records one); events (what people did in the app); reviews (the newest reviews); ads (Apple Ads and Google Ads: when each campaign ran, what it spent, what it brought, cost each, buyers when known, changes, search terms, next steps); why (why a number moved: the days far from usual in the period, or one day or range explained, causes biggest first with how much each explains); timeline (what happened when, oldest first: ads starting and stopping, campaign changes, releases, days far from usual with their top cause, best days, milestones, bursts of reviews); journey (how far people get, step by step, and where they stop: from the store to the first open, then inside the app (the app's own steps: onboarding, sign-in, the main thing people do, buying, coming back) with the biggest drop and what the people who left there did last (for Apparent's own app: from apparent.fyi to the first alert)); features (which features people use: each one's share of the period's people, days each, people on a usual day, and which are loved, hidden gems (few use them, those who do keep coming back), tried and not kept, or hardly used); properties (people active in the period by what the app told us about them (plan, language…), at their latest value).

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": {
      "app": "<app>",
      "topic": "<topic>"
    },
    "name": "app_topic"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesWhich app: its id or part of its name. Known apps: .
topicYesWhich part to answer about.
metricNoWhich number to explain: downloads (default when the app has store numbers), people, new_people or money.
periodNo7d (default), 30d, 90d, 12m, today, yesterday, all, 14d, a day like 2026-09-21, or a range like 2026-09-01..2026-09-30.
sourceNoOnly one source's numbers (app_store, google_play, revenuecat, admob, mixpanel, sdk). Leave out for everything together, counted once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / topic / enum
      Previous value: -[
      -  "numbers",
      -  "highlights",
      -  "countries",
      -  "sources",
      -  "buyers",
      -  "problems",
      -  "versions",
      -  "visits",
      -  "events",
      -  "reviews",
      -  "ads",
      -  "why",
      -  "timeline",
      -  "journey",
      -  "properties"
      -]New value: +[
      +  "numbers",
      +  "highlights",
      +  "countries",
      +  "sources",
      +  "buyers",
      +  "problems",
      +  "versions",
      +  "visits",
      +  "events",
      +  "reviews",
      +  "ads",
      +  "why",
      +  "timeline",
      +  "journey",
      +  "features",
      +  "properties"
      +]
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

readOnlyHint=true already declares the safety profile, so the description earns credit only for the extra context it does add: data availability caveats ('when the app records one', the Apparent-specific journey exception). It does not disclose response size, whether topics differ in cost or latency, or how a missing source is handled.

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

Conciseness2/5

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

The entire definition is one semicolon-chained run-on sentence of roughly 200 words. The useful routing information is buried mid-sentence, and nothing is front-loaded as a lead statement of what the tool does.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Topic coverage is exhaustive and there is no output schema to explain, but a tool with 16 heterogeneous return shapes and overlapping siblings needs at least a note on selection vs alternatives or on result characteristics. That absence leaves the definition incomplete for correct invocation.

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% and three enums are self-documenting, but the description adds real meaning beyond the schema's 'Which part to answer about' by spelling out the contents of each of the 16 topic values. That is genuine semantic value the agent cannot get from the enum names alone.

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?

States a specific resource and scope: one topic for one app, then enumerates every topic the tool answers. It is clear what the tool returns, but it never distinguishes itself from siblings like timeline, why_did_it_change, or today, even though two of its topic values (why, timeline) overlap with them by name.

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

Usage Guidelines2/5

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

No sentence says when to use app_topic with topic='why' instead of why_did_it_change, or topic='timeline' instead of the timeline tool. The agent is left to infer routing from the enum listing alone.

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