Skip to main content
Glama

open_branch

Needs sign-in (connect this server with OAuth, or pass an API key as the Authorization: Bearer header). With job from change_wait: create a private draft from your own private test upload; title and notes come from the player’s DATA. With no job: posts your test build next to the live alpha game, without changing what the game page runs. When request is omitted, its title becomes its votable ask; it takes one of the same four build spots. An explicit request keeps the existing pick-up rules. Stage the build with upload_token, as its reply says for this connection (on a full one: Stage a local build folder with Node 22+: download https://yougame.co/upload-build.mjs, then run node upload-build.mjs with YOUGAME_URL=https://yougame.co and YOUGAME_UPLOAD_TOKEN (from upload_token) or YOUGAME_API_KEY set; on an "Ideas and test builds only" one: upload-build.mjs with the build folder or its zip), then call this with its uploadId and request = the request's id. For a web or native test build on an owner-governed game (owner or maintainers mode), the owner or an approver puts any open, playable test build in from the game page, including while it is being tested; tester counts inform their decision. Community-governed games merge by vote: players confirm it works, then vote, one player one vote; at two-thirds yes with enough votes it merges after a 24-hour veto window. It is released as the game's next version and credited to you. To replace your web test build, stage a revised upload and call revise_branch; alpha_task gives its current branch.build and any send-back notes. On a game whose test builds are source patches (alpha_task says so in native), send no upload: variants is [{ kind: "native-source", patch: }]; YouGame keeps it privately, builds it on its build machine and offers the build offline in the desktop app to the game's testers. For a YG Dolphin pack, use one variant {kind: 'pack-changeset', changeset: {base: pack.base, files: {path: text}, deleted: []}} from alpha_task or alpha_board. Read the editable text with pack_read_file. Submitting shares your title and idea on the game's board. Only the owner, testers and you can play it. Who puts it in follows the game's governance: the owner or an approver on owner-governed games; by vote on community-governed games. No upload or binary changes; only the manifest's editable_fields may change. At most 64 touched files (MAX_SUBMIT_FILES) and 2097152 UTF-8 bytes (MAX_SUBMIT_BYTES). A stale base (409) means re-read alpha_task or alpha_board, reapply and retry.

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": {
      "slug": "<slug>",
      "variants": "<variants>"
    },
    "name": "open_branch"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobNoYour change_wait job id: opens a private draft, or finishes its tweak. No claim or slot is needed. Only the player proposes it.
kindNo
noteNoOptional, up to 120 characters: a line pinned under the test build's title for players, e.g. "Jump works, the new level is not in yet". When you know a build is broken or partly done, pin a line saying so; it clears on your next revision. build_note changes or clears it later.
slugYesThe alpha game's slug.
notesNoShown to every player under "What changed" on the test build. Write what a player will see or feel changed, in plain words, one to three sentences, e.g. "Shows the round number in big yellow letters above the ring." No tools, file names, commands, test results, environment notes or apologies: those go in verification. Up to 2000 characters.
titleNoWithout job: 3-120 characters, for players: what this branch changes, e.g. "Jump is easier to time" or "Results screen: three looks". A job takes its title from the player’s change.
requestNoOptional without job: the request you picked up (alpha_board lists the claims). Omit it to make an ask from the build's title.
uploadIdNoThe staged upload (32 hex characters) for a web test build. Same as variants: [{ uploadId }]; send one or the other.
variantsYesOne build: { uploadId } for a web game, { kind: "native-source", patch } for a native one, or { kind: "pack-changeset", changeset: { base, files, deleted } } for a YG Dolphin pack.
team_checkNoA check for your own team. Never asks players to try it or enters a top list.
verificationNoOptional: how you checked the build (commands, tests, what passed, what you could not run). Never shown to players and not stored with the test build: tell the person you build for in your own reply.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / note
      Added value: +{
      +  "description": "Optional, up to 120 characters: a line pinned under the test build's title for players, e.g. \"Jump works, the new level is not in yet\". When you know a build is broken or partly done, pin a line saying so; it clears on your next revision. build_note changes or clears it later.",
      +  "maxLength": 120,
      +  "type": "string"
      +}
  2. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the write/safety profile is supplied structurally. The description adds genuinely useful behavior beyond that: auth requirements, visibility ('only the owner, testers and you can play it'), governance/merge-by-vote with a 24-hour veto window, size caps (64 files, 2097152 bytes), and the 409 stale-base recovery. That is real added value, but it is delivered as an undifferentiated run-on rather than organized behavioral notes.

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?

A single sprawling paragraph with nested parentheticals and inline command examples. Individual facts are useful, but they are not front-loaded or grouped, so the agent must parse the whole block to find the operating rule.

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?

For an 11-parameter tool with branching submission modes and no output schema, the description covers auth, staging, limits, governance, visibility, merge outcome and the 409 retry path. Nothing essential to calling it correctly appears to be missing.

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 91%, so the baseline is 3; the description earns above that by explaining the interplay the schema cannot: title and notes deriving from the player's DATA when job is set, notes vs verification being player-facing vs private, and request becoming a votable ask when omitted. Some parameters (team_check, the top-level kind) get no treatment in the description.

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 states a specific action (open a branch / post a test build) and enumerates the distinct modes: job vs no job, web upload, native-source patch, and pack-changeset. It is recognizable, but the core verb+resource is buried mid-paragraph rather than stated up front.

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 explicitly routes the agent: 'With job from change_wait' versus 'With no job', and names the alternative for replacement work ('To replace your web test build, stage a revised upload and call revise_branch'). It also names the prerequisite tools (upload_token, alpha_task, alpha_board, pack_read_file) and the condition that selects each path.

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