Skip to main content
Glama

close_branch

Destructive

Needs sign-in (connect this server with OAuth, or pass an API key as the Authorization: Bearer header). Ends a test build (branch) of an alpha game. On owner-governed games (owner or maintainers mode), the owner or an approver puts an open, playable test build in from the game page, including during testing. Community-governed games merge by vote. This tool also withdraws test builds: a builder may withdraw their own (outcome "closed"), which frees its slot for another open test build. The game's creator may also turn one down ("rejected") or withdraw it, and outcome "merged" records that a build they shipped with update_game folds it in (ship:true releases the branch's own build only when it is the creator's upload).

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>",
      "branch": "<branch>",
      "outcome": "<outcome>"
    },
    "name": "close_branch"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWith ship: major or minor (default).
noteNoUp to 500 characters, shown to players: how it ended and why.
shipNoWith outcome merged: release the winning build itself as the next version (minor unless kind is major).
slugYes
branchYesThe branch id from alpha_board or open_branch.
winnerNoFor a merged choice: the key of the build that won.
outcomeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the bar is lower, yet the description adds substantive behavior: outcome semantics (closed frees the slot, rejected, merged), that merged records a fold-in by update_game, and the ship:true release rule. It omits what happens to competing builds and error/rollback behavior, keeping it from 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 description is one long, clause-heavy paragraph that buries the core action behind an auth preamble and an aside about how builds are opened. Several sentences are run-ons with nested parentheticals, and key information (what the tool does) is not front-loaded.

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?

For a 7-parameter destructive mutation with no output schema, the description covers outcomes, permissions, and the ship interaction reasonably well. It still omits what the caller gets back, whether the action is reversible, and how conflicts with existing builds are resolved.

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 71%, and the description adds genuine meaning beyond the schema: it explains the three outcome values and their consequences, and qualifies ship (releases the branch's own build only when it is the creator's upload) and kind (major/minor with ship). It leaves winner and note unaddressed, but the schema already documents those.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The second sentence states a clear verb+resource: "Ends a test build (branch) of an alpha game." However, the surrounding text is muddled: it describes opening builds ("the owner or an approver puts an open, playable test build in") and uses inconsistent terminology ("test build (branch)"), and it never distinguishes this from the close_test_build sibling. An agent can extract the purpose but must work for it.

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?

It gives real governance context — owner/maintainer mode vs. community-governed games that merge by vote — and enumerates who may perform which outcome (builder withdraws own, creator rejects or withdraws). That is useful when-to-use guidance, but there is no explicit routing to alternatives such as close_test_build or close_test_session, and the sentence about opening builds is about a different operation.

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