Bot-Hosting.net

Change the startup settings

deployments_updateStartup

Destructive

Change runtime / version / entry file / start command (queues a rebuild). The start command is a FULL SHELL LINE run at every boot: it can install and build before starting - e.g. 'npm install && npm run build && exec node build/index.js'. There is no other way to run build steps, and there does not need to be: put them here and restart. Keep the install step: a command that only starts the app stops installing dependencies at boot. A new runtime brings its own default version, entry file and start command unless you pass them. Changing the TYPE (e.g. nodejs to static) reinstalls from scratch and deletes every file: it needs wipeFiles: true, so switch first and write the files after. Writes made during a reinstall wait until it is done.

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": {
      "id": "<id>"
    },
    "name": "deployments_updateStartup"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`kind`	No
`engine`	No
`runtime`	No	Omit to keep the current runtime.
`entryFile`	No	Omit to keep the current entry file.
`wipeFiles`	No	Required when the change deletes every file in the deployment (a new type, e.g. nodejs to static).
`startCommand`	No	Full shell line, run in the container at every boot, from the volume root (/home/container, where files.tree starts): never cd to /app or any other path. Chain install/build/start with &&. A server must bind 0.0.0.0 and the SERVER_PORT env (or pass the port explicitly). The last step is exec'd so that Stop works, and exec is added for you if you leave it out. null = the runtime default, which already installs from package.json / requirements.txt. Omit to keep the current command.
`runtimeVersion`	No	Runtime version as a string, e.g. "24"; a bare number is accepted too. Omit to keep the current one.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotent, and the description goes well beyond them: a type change 'reinstalls from scratch and deletes every file' and requires wipeFiles: true, a new runtime resets default version/entry file/start command, and writes during a reinstall are queued. These are precisely the consequences an agent must know before a destructive mutation.

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?

Dense but front-loaded: the affected settings and the rebuild side effect come first, followed by the risky type-change caveat. A few clauses are repetitive ('there does not need to be: put them here and restart'), but every sentence carries operational information.

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?

For an 8-parameter destructive mutation with no output schema, the description covers the hazards (wipe on type change, queued writes, runtime resets) and the start-command contract. It does not say how to observe the triggered rebuild afterward (e.g. via a check or logs sibling), which is the one remaining gap.

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 63%, and the description compensates well for the important fields: startCommand is defined as a full shell line run from the volume root with exec semantics, null meaning the runtime default, and port/env expectations; wipeFiles and runtime defaults are also explained. The 'omit to keep current' convention is left to the schema, so it does not fully close the gap.

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 ('Change') applied to named settings (runtime, version, entry file, start command) and adds the side effect ('queues a rebuild'). An agent can immediately tell this apart from the read-side sibling deployments_getStartup.

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?

Gives explicit operational guidance: build/install steps belong in the start command because 'there is no other way to run build steps', keep the install step, and switch type first then write files. It never names a sibling tool such as deployments_update or deployments_check as the alternative, so routing is implied rather than stated.

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

All Bot-Hosting.net 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.

Resources

Need Help?