Skip to main content
Glama
Sign In

Shipvo

by io.github.shipvo
OverviewDiscussionsAdmin

publish_preview

Build the app in PN_APP_DIR (or the current folder) with the simulated device and publish a shareable web preview to here.now, no account. The link is PUBLIC and expires in 24 hours; claimUrl keeps it. Returns { url, claimUrl, expiresAt }. Needs @shipvo/cli (npx). Slow: waits up to wait_ms (default 20000), then returns { status: "running", job }; call job_status with that job. Calling again while it runs returns the same job.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "publish_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_msNoHow long to wait for the result before returning { status: "running", job } (default 20000). Read it later with job_status.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / wait_ms
      Added value: +{
+  "description": "How long to wait for the result before returning { status: \"running\", job } (default 20000). Read it later with job_status.",
+  "maximum": 55000,
+  "minimum": 0,
+  "type": "integer"
+}
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: the link is PUBLIC, expires in 24 hours, claimUrl can keep it, an external CLI (@shipvo/cli via npx) is required, and the call is slow by design. These are real operational facts an agent needs. Not a perfect 5 only because it does not address what happens after expiry or whether the preview survives the session.

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 build/publish intent and packs a lot of needed detail with no filler. It is slightly run-on and mixes return format, cost, and polling in one dense block, but no sentence is wasteful.

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?

No output schema exists, yet the description specifies the returned shape ({ url, claimUrl, expiresAt } and the running-job variant), the side effects (public, 24h expiry), and the follow-up call. For a one-parameter publishing tool this is fully self-sufficient.

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% and the single wait_ms parameter is fully documented in the schema, so the baseline would be 3. The description goes further by explaining the consequence of the value (returns { status: "running", job } afterwards) and the required next action, giving it meaning beyond the schema text.

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?

Specific verb chain (build the app, publish a shareable web preview), names the target directory resolution (PN_APP_DIR or current folder) and the destination (here.now), so it is clearly distinct from siblings like job_status or create_app.

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?

Explicitly states the follow-up path when the publish is slow: if a running job is returned, call job_status with that job. It also notes re-calling while running returns the same job. It does not name a when-not-to-use case or an alternative publishing tool, so it falls short of a 5.

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

All Shipvo toolsInspect
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