Skip to main content
Glama

Session

glitchless_session
Read-onlyIdempotent

One play session, or without session_id the latest sessions (who played, when, for how long, how far they got, the session type), to find one: the developer's own playtest to mark with glitchless_mark_known (player), a crash to open. With session_id, by default a summary an agent can hold: the device, then each level in the order it was played (when it was first reached, the time spent on it, tries, completions, deaths and their causes, the game's own events counted, hitches with the worst and their causes, frame rate, errors, rage inputs with where the player stood, and how it ended there), time outside levels (menus, a title screen), the worst hitches, errors, bug reports, and the outcome (crashed, rage quit, the last level). With level or types, the events themselves (levels with their attributes, deaths with positions, errors, hitches with causes, custom events, counters once a window, disconnects, agent annotations), each with at_s, seconds from the start: types "death,hitch" or a custom event name "room_done"; "frames" adds the per-5s frame windows. view "timeline" gives every event (long: a 10-minute session has hundreds). Use with session ids from errors, hitches, rage quits, rage inputs or a match. A game server's session (service ".server") gives its tick windows.

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_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
viewNo"summary" (default, unless level or types is given): level by level; "timeline": the events themselves
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.
levelNoOnly this level's events: its own and what happened while it was played
limitNoWith the timeline: at most this many events (default 150), from the first
typesNoOnly these, comma-separated: event types (death, hitch, error, custom, level_start, bug_report…), custom event names (room_done), or "frames" for the frame windows
serviceNoGame service name (defaults to the most recently active game)
versionNoOnly include sessions from this game version
session_idNoSession id (s_…); without it, the latest sessions
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

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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."
  2. Changed10 schema fields changed
    • addedInput schema / properties / env
      Added value: +{
      +  "description": "Only include sessions from this environment, e.g. \"prod\" (what the game passes to init; builds a developer runs usually send \"dev\")",
      +  "type": "string"
      +}
    • addedInput schema / properties / hours
      Added value: +{
      +  "description": "Look-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.",
      +  "maximum": 9600,
      +  "minimum": 0.25,
      +  "type": "number"
      +}
    • addedInput schema / properties / level
      Added value: +{
      +  "description": "Only this level's events: its own and what happened while it was played",
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "With the timeline: at most this many events (default 150), from the first",
      +  "maximum": 1000,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / session_id / description
      Previous value: -"Session id (s_…)"New value: +"Session id (s_…); without it, the latest sessions"
    • addedInput schema / properties / session_type
      Added value: +{
      +  "description": "\"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",
      +  "enum": [
      +    "user",
      +    "tester",
      +    "synthetic",
      +    "all"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / types
      Added value: +{
      +  "description": "Only these, comma-separated: event types (death, hitch, error, custom, level_start, bug_report…), custom event names (room_done), or \"frames\" for the frame windows",
      +  "type": "string"
      +}
    • addedInput schema / properties / version
      Added value: +{
      +  "description": "Only include sessions from this game version",
      +  "type": "string"
      +}
    • addedInput schema / properties / view
      Added value: +{
      +  "description": "\"summary\" (default, unless level or types is given): level by level; \"timeline\": the events themselves",
      +  "enum": [
      +    "summary",
      +    "timeline"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "session_id"
      -]
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavior: default summary versus raw events, that 'timeline' is long ('a 10-minute session has hundreds'), the default limit of 150 events, that hours past 744 are answered by day, and that a key scoped to one game refuses calls naming another. It does not discuss latency or rate limits, keeping it just below top marks.

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

Conciseness3/5

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

Every clause carries information, but it is delivered as two sprawling run-on sentences dense with nested parentheses and broken fragments ('a crash to open'). The primary case is front-loaded, yet the mode-selection logic could be split into bullets for far easier scanning.

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 11 optional parameters, no output schema, and only safety annotations, the description carries the burden well: it describes what the summary contains (device, per-level timing, deaths and causes, hitches, errors, outcome) and what the event stream contains. The main gap is guidance on navigating large result sets beyond the timeline limit.

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 genuinely adds meaning: types accepts event types, custom event names like 'room_done', or 'frames'; limit applies only to the timeline; session_type semantics are tied to how findings read production player sessions; and service '<game>.server' returns tick windows.

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 description names the resource (a play session) and its two modes: a single session by session_id, or the latest sessions without one, and it enumerates the returned fields (who played, duration, progress, session type). It does not differentiate itself from the glitchless_events sibling, which appears to overlap heavily with the level/types event mode, so it falls short of 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 Guidelines4/5

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

It gives concrete entry points: 'Use with session ids from errors, hitches, rage quits, rage inputs or a match', and it names the downstream workflow (a developer's own playtest to mark with glitchless_mark_known, a crash to open). It also explains when to pick summary vs level/types vs timeline. It stops short of explicit exclusions against the sibling event-oriented tools.

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