Skip to main content
Glama

Player funnel

glitchless_player_funnel
Read-onlyIdempotent

Player experience per level: sessions that started vs completed each level, attempts, deaths per session and their causes, fails, abandons and the attempts a disconnect ended (never counted as fails), median and slowest clear times, rage quits (quit ≤20s after dying), session length distribution, recent rage quits with positions, and recent rage inputs (one key mashed: the SDKs count them in kpis.rage_inputs) with their level, time, key and, for a game that sends positions, where the player stood. With by, each level per value of what describes the attempt: an attribute the game passed to levelStart ("tier", "difficulty", "party_size"; a list such as "build" counts under each element), a session property ("$class") or a split ("$platform"): clears and wipes by difficulty, by group size, by class; level keeps one level; count "runs" counts each run once at each level it reached (a roguelite's biomes). Also retention: of the players first seen each day, the share back 1, 7 and 30 days later (D1, D7, D30; hours of 48 or more for D1), and with by_prop per value of a session property (spenders against the rest). Retention needs player IDs: status "anonymous" means the game sends none, and privacy "install" in the SDK turns them on. With hotspots, for a game that sends positions: where players die instead, on one level (level), in one zone (zone, as the game passes it to setZone) or, with neither, anywhere in the game (a hub or lobby with no level set): clustered death positions in world coordinates (x range, share of the place's deaths, top cause, rage quits at that spot), the bounds and the place's stats (a level's completion; a zone's sessions, deaths and rage quits), to find a difficulty spike and then the level data around it.

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": "glitchless_player_funnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNoSplit each level's attempts: an attribute of its levelStart ("tier"), a session property ("$class") or $platform, $browser, $device_tier, $link, $graphics, $site
envNoOnly include sessions from this environment, e.g. "prod" (what the game passes to init; builds a developer runs usually send "dev")
gameNoThe game, by name or id, when signed in to a workspace (glitchless_list_games lists them); later calls keep it. With a key for one game (gl_sk_…), a call that names another game is refused: sign in to the workspace to reach every game.
zoneNoWith hotspots: the zone instead of a level, e.g. "hall" (neither: the whole game)
countNo"runs": each run (setGroup("run")) counted once at each level it reached
hoursNoLook-back window in hours (default 24), as far back as the workspace keeps data on Glitchless Cloud (the answer says when it starts later than asked). Past 744 (31 days) answers are by day.
levelNoWith by or count: only this level; with hotspots: the level, e.g. "level-3"
propsNoOnly sessions with these session properties (what the game set with setProperties): { rank: "diamond" }, or a list of values for any of them, { rank: ["diamond", "master"] }; "(none)" keeps the sessions without one. glitchless_events lists the properties and their values. Read from the sessions, so over 31 days or less
by_propNoRetention per value of this session property, e.g. "spender"
serviceNoGame service name (defaults to the most recently active game)
versionNoOnly include sessions from this game version
hotspotsNoWhere players die, instead of the funnel: on level, in zone, or with neither anywhere in the game
session_typeNo"user": players only; "tester": people on TestFlight and other test builds only; "synthetic": bots, playtests and store test devices only; "all" or unset: every session. Findings (glitchless_triage, and the overview's) read the production sessions of players unless env or session_type is given
steam_branchNoOnly include sessions that ran this Steam branch ("public", or a beta's name); games that use Steamworks send it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / by / description
      Previous value: -"Split each level's attempts: an attribute of its levelStart (\"tier\"), a session property (\"$class\") or $platform, $browser, $device_tier, $link, $graphics"New value: +"Split each level's attempts: an attribute of its levelStart (\"tier\"), a session property (\"$class\") or $platform, $browser, $device_tier, $link, $graphics, $site"
  2. Changed1 schema field changed
    • changedInput schema / properties / by / description
      Previous value: -"Split each level's attempts: an attribute of its levelStart (\"tier\"), a session property (\"$class\") or $platform, $browser, $device_tier, $link"New value: +"Split each level's attempts: an attribute of its levelStart (\"tier\"), a session property (\"$class\") or $platform, $browser, $device_tier, $link, $graphics"
  3. Changed1 schema field changed
    • changedInput schema / properties / game / description
      Previous value: -"The game, by name or id, when signed in to a workspace (glitchless_list_games lists them); later calls keep it. Ignored with a key for one game."New value: +"The game, by name or id, when signed in to a workspace (glitchless_list_games lists them); later calls keep it. With a key for one game (gl_sk_…), a call that names another game is refused: sign in to the workspace to reach every game."
  4. Changed2 schema fields changed
    • changedInput schema / properties / hotspots / description
      Previous value: -"With level: where players die on it, instead of the funnel"New value: +"Where players die, instead of the funnel: on level, in zone, or with neither anywhere in the game"
    • addedInput schema / properties / zone
      Added value: +{
      +  "description": "With hotspots: the zone instead of a level, e.g. \"hall\" (neither: the whole game)",
      +  "type": "string"
      +}
  5. Changed2 schema fields changed
    • addedInput schema / properties / hotspots
      Added value: +{
      +  "description": "With level: where players die on it, instead of the funnel",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / level / description
      Previous value: -"With by or count: only this level"New value: +"With by or count: only this level; with hotspots: the level, e.g. \"level-3\""
  6. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With readOnly/idempotent/non-destructive annotations already covering safety, the description still adds substantive behavior: disconnects are never counted as fails, rage quits are defined as quitting ≤20s after dying, retention requires player IDs and fails under status "anonymous" or privacy "install", answers past 744 hours are by day, and results may start later than requested. It stops short of rate limits or payload-size behavior, so a 4 rather than a 5.

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 main purpose is front-loaded in the first clause, but the body is a single wall of text with deeply nested parentheses that repeatedly bury critical qualifiers ("never counted as fails", "hours of 48 or more for D1"). Several clauses try to do three jobs at once; breaking it into labeled sections (funnel / retention / hotspots) would preserve the content at a fraction of the reading cost.

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 14-parameter tool with nested objects and no output schema, the description covers the three modes, the derived metrics, prerequisite conditions (player IDs for retention, positions for hotspots), and lookback caveats. Remaining gaps are minor: default behavior when no level/zone/by is supplied is only partly spelled out and the exact response shape is described in prose rather than enumerated.

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 the baseline is 3, but the description adds meaning the schema alone does not: how by interacts with level and count ("runs counts each run once at each level it reached"), how list-valued attributes like "build" split per element, and how hotspots changes the meaning of level and zone. These cross-parameter interactions are genuine added value beyond the field descriptions.

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 names concrete metrics per level (started vs completed sessions, attempts, deaths and causes, fails, abandons, clear times, rage quits, session length), plus two explicit modes: retention (D1/D7/D30) and hotspots (clustered death positions). The scope is unmistakable. It does not explicitly contrast itself with siblings like glitchless_session or glitchless_match, which keeps it below a 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?

Usage is implied through mode selection (by/count for splits, hotspots for death clustering, by_prop for retention splits) and one workflow hint: use hotspots "to find a difficulty spike and then the level data around it." There is no explicit statement of when to prefer this tool over a sibling or what it should not be used for; the reader must infer the routing.

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