Skip to main content
Glama

upload_app

Upload a zipped iOS/tvOS simulator app, Android APK, or Roku channel ZIP to return an app_id for starting a cloud device session.

Instructions

Upload an app build (zipped simulator .app for iOS/tvOS, .apk for Android/Android TV, or a Roku channel .zip) and return its app_id for dev_start. The MCP equivalent of vibeview upload-app.

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": {
      "file": "<file>"
    },
    "name": "upload_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesPath to the build file on this machine: a zipped iOS/tvOS simulator .app, an Android/Android TV .apk, or a Roku channel .zip.
nameNoApp name (auto-detected from the build if omitted).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only supply readOnlyHint=false, so the description must carry the rest — and it does disclose the accepted build artifacts, that the operation yields a persistent app_id, and that name may be auto-detected. It omits overwrite/duplicate behavior and any size or auth constraints, which keeps it short of 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.

Conciseness5/5

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

Two sentences, front-loaded with the action and accepted inputs, followed by the output and next-step linkage. The CLI-equivalence note is short and orients agents familiar with the command line; nothing is redundant.

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 two-parameter tool with a clear return value stated inline despite having no output schema, this is nearly complete. Minor gaps remain around failure modes (invalid build type, path not found) and whether re-uploading replaces an existing app.

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 coverage is 100%, and both parameters are already documented in the schema, including the path formats and name auto-detection. The description restates the accepted file types but adds no new syntax, path-resolution, or omission semantics beyond the schema baseline.

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 (upload) and resource (app build), enumerates the accepted formats per platform, and names the downstream consumer (dev_start) plus the returned value (app_id). An agent can distinguish this from list_apps/list_builds/dev_start without opening the schema.

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?

The phrase 'return its app_id for dev_start' establishes the workflow position: this is the prerequisite step before starting a dev session. It does not state explicit exclusions (e.g., when to reuse an existing app via list_apps instead of re-uploading), so it falls short of a full when/when-not guide.

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