Handsome Hosting

Deploy

deploy

Destructive

Start a deploy into an existing running service: from an uploaded archive (uploadId, after its PUT), or archive as the base64 of a gzip tar for a tiny project under 1 MiB. Returns the deploy id; the deploy runs on its own. The service must already exist; a project with no server yet is ordered, not deployed.

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": {
      "serviceId": "<serviceId>"
    },
    "name": "deploy"
  }
}

Input Schema

Name	Required	Description
`archive`	No	base64 of a small .tgz (under 1 MiB); a larger project comes as uploadId
`uploadId`	No	the upload id, after its PUT
`preflight`	No	the pre-flight report of the checks run on the person's machine; required: the call refuses without a passing one
`serviceId`	Yes	the id of a service on this account

Output Schema

Name	Required	Description	Default
`ok`	Yes
`data`	No
`error`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 26, 2026

changedInput schema / properties / archive / description

Previous value: -"base64 of a small .tgz (under 1 MiB); larger projects use request_upload"New value: +"base64 of a small .tgz (under 1 MiB); a larger project comes as uploadId"

changedInput schema / properties / preflight / description

Previous value: -"the pre-flight report from the preflight tool protocol; required: the call refuses without a passing one"New value: +"the pre-flight report of the checks run on the person's machine; required: the call refuses without a passing one"

changedInput schema / properties / serviceId / description

Previous value: -"the service id from list_services"New value: +"the id of a service on this account"

changedInput schema / properties / uploadId / description

Previous value: -"from request_upload, after the PUT"New value: +"the upload id, after its PUT"

First observedOct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the bar is lower, and the description adds real context: the call "Returns the deploy id; the deploy runs on its own," telling the agent the operation is asynchronous and to poll deploy_status rather than wait. It also states the service must pre-exist, reinforcing the refusal paths. It does not say what content of the running service is replaced by the new deploy, which is the main gap for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with the primary mode stated first, the size-limited fallback second, and the lifecycle caveat last. No filler, and the async return behavior is front-loaded where it matters.

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 a destructive, asynchronous tool with a nested preflight object and an output schema, the description covers the prerequisite, the two ingestion paths, and the fire-and-forget execution model. What remains unsaid — the effect on the currently running service and the deploy/rollback relationship — would be valuable but is partly recoverable from the sibling rollback and deploy_status.

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?

Schema description coverage is 100%, so every parameter, including the nested preflight report, is already documented in structured fields. The description restates the uploadId-vs-archive split and adds the "after its PUT" sequencing hint, but adds nothing for preflight or serviceId beyond the schema. Baseline 3 is appropriate.

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?

Opens with a specific verb and resource ("Start a deploy into an existing running service") and enumerates the two input modes, so the agent knows exactly what the call does. It implicitly separates itself from create_project ("a project with no server yet is ordered, not deployed") but never names the closest siblings, redeploy and deploy_status, so the differentiation is not fully airtight.

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 a clear precondition (service must already exist) and a decision rule between the two archive modes: uploadId for a normal project, inline base64 gzip tar only for "a tiny project under 1 MiB." It also states the negative case (no server yet → ordered, not deployed). Missing an explicit steer to redeploy for an already-deployed service.

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

All Handsome Hosting 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?