Skip to main content
Glama

start_test_session

Needs sign-in (connect this server with OAuth, or pass an API key as the Authorization: Bearer header). Run a staged build in the isolated YouGame testing site, with 2–10 disposable signed-in players, real social features and multiplayer. Does not publish. Returns separate player login URLs, a build fingerprint, and an untested scenario checklist. Open each player loginUrl in a separate browser context/profile (tabs alone share login cookies). Use real browser inputs on the game's actual menus. Test desktop at 1440x900 and touch at 375x812, capture screenshots, console errors, failed requests, and interaction steps. For online play, seat two identities, verify Casual/Ranked/Friends, Ready, synchronized play, result, rematch, disconnect/rejoin, and an invite accepted from a fresh page. To test friend requests, use strangers or unfriend a disposable player through the UI. Record results with record_test_evidence, then read test_report before prepare_submission. Static checks and backend counts do not prove runtime behavior or good UX. Payments and voice are not enabled in the test environment; report them as untested. Close the session when done. Login URLs are private credentials and expire with the session.

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": {
      "uploadId": "<uploadId>"
    },
    "name": "start_test_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
listingNo
playersNo
uploadIdYes
relationshipsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / listing / properties / button_default
      Added value: +{
      +  "description": "How the YouGame button over the game starts. \"fade\" (default): it shows at start, then fades; a game that calls YouGame.setGameState hides it while playing and shows it while paused or in a menu. \"hidden\": fully hidden from the start; players open YouGame with Shift+Tab or Back+Start, and a player's own choice still wins. Only when the creator asked for it.",
      +  "enum": [
      +    "fade",
      +    "hidden"
      +  ],
      +  "type": "string"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare it is a non-read-only, non-destructive, non-open-world call. The description adds real behavioral context beyond that: OAuth or Bearer API-key auth is required, the run does not publish, the session must be closed, login URLs are private credentials that expire with the session, and payments and voice are disabled in the environment and must be reported as untested.

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?

Purpose, prerequisites and return values are front-loaded, and the procedural testing instructions follow in a logical order. It is dense rather than padded, though the long mid-section of viewport, screenshot and multiplayer checklist items could be tightened slightly.

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 return burden and does it: separate player login URLs, a build fingerprint, and an untested scenario checklist. Combined with the auth prerequisite, the per-player browser-context requirement and the environment limitations, an agent has everything needed to invoke and act on this tool.

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?

Top-level schema coverage is 0% — uploadId, players and relationships carry no property descriptions. The description partially compensates by naming the 2–10 player range and by pointing at strangers/friend testing ("use strangers or unfriend a disposable player through the UI"), which hints at the relationships enum, but uploadId is never explained and neither parameter is described semantically.

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?

Opens with a specific verb and resource: "Run a staged build in the isolated YouGame testing site, with 2–10 disposable signed-in players, real social features and multiplayer. Does not publish." The scope (isolated test site, staged, non-publishing) separates it cleanly from publish_game and from evidence/report siblings.

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 an explicit workflow with named alternatives: record results with record_test_evidence, then read test_report before prepare_submission, and close_test_session when done. It also states an exclusion — static checks and backend counts do not prove runtime behavior — so the agent knows when this tool is required rather than optional.

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