HotCodePush

Create a channel

create_channel

Create a channel of an app: a named stream of releases a device follows, such as "staging", "beta" or a preview channel per pull request. Use this to separate audiences. isProtected reserves releases, pause, resume and deletion for Owners and Admins, the setting for production; isDiscoverable lets a device switch to the channel by name; expiresAt ends a preview channel on its own; the failure* fields set the auto-pause policy, null keeping the default. The name takes letters, digits, - and _, up to 64 characters, unique per app, and counts against channelCountPerAppLimit. Returns the created channel; pass its id to create_release. Do not use this to publish an update (use create_release) or to pause an existing channel (use pause_channel).

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": {
      "appId": "<appId>",
      "name": "<name>"
    },
    "name": "create_channel"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The name of the channel, e.g. "staging".
`appId`	Yes	The id of the app, e.g. "a1b2c3d4-0000-4000-8000-000000000000". Use `list_apps` to look it up by name.
`expiresAt`	No	When the channel stops serving releases, ISO 8601 in UTC, e.g. "2026-12-31T00:00:00Z" for a preview channel; null never expires. Optional.
`isProtected`	No	Whether releases, pause, resume and deletion take an Owner or Admin, e.g. true for production. Optional.
`failureAction`	No	What auto-pause does when a release fails above the threshold: "pause" stops offering it and devices on it keep it, "revoke" also moves them back, "notify" only notifies, "none" evaluates the rule but acts on nothing; null keeps the default. Optional.
`isDiscoverable`	No	Whether a device may switch to the channel by name at runtime, e.g. true for a beta channel testers opt into. Optional.
`failureThresholdPercent`	No	The share of applied updates that may fail before auto-pause acts, e.g. 5; null keeps the default. Optional.
`failureMinimumUpdateCount`	No	The applied updates a release needs before the threshold is judged, e.g. 50; null keeps the default. Optional.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-read-only, non-destructive, open-world call. The description adds real behavioral context: the channel name must be unique per app and consumes a `channelCountPerAppLimit` quota, `isProtected` gates who can pause/resume/delete, `expiresAt` self-terminates a preview channel, and the tool returns the created channel whose `id` feeds `create_release`.

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?

Front-loaded with the core definition, then parameter semantics, then the exclusion clause last. Dense but nearly every clause carries information; a few items (the name character rule) duplicate the schema and could be trimmed.

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 8-parameter creation tool with no output schema, the description covers the return value ('Returns the created channel'), the downstream linkage via `id`, quota cost, and per-field intent — nothing an agent needs to call it correctly is 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 100%, so the baseline is 3, but the description adds cross-parameter framing the per-field schema does not: the `failure*` fields collectively define one auto-pause policy where null keeps the default, and it characterises `isProtected` as 'the setting for production' and `isDiscoverable` as runtime opt-in. The name grammar largely restates the schema pattern.

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?

States a specific verb and resource ('Create a channel of an app') and immediately defines what a channel is: 'a named stream of releases a device follows'. Concrete examples ('staging', 'beta', a preview channel per pull request) make the resource unambiguous against 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 positive guidance ('Use this to separate audiences') plus explicit exclusions naming the correct alternatives: 'Do not use this to publish an update (use create_release) or to pause an existing channel (use pause_channel)'. This is exactly the when/when-not/alternative structure needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All HotCodePush tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.