Skip to main content
Glama

flipper_launch_fap

Launch an external .fap app by its full SD path and return immediately, then use screenshot and navigation tools to view and control the running app.

Instructions

Launch an external .fap app by its full SD path, e.g. '/ext/apps/GPIO/esp32_wifi_marauder.fap'. External apps are NOT in loader list (only built-ins are), and launching a GUI app does not return a CLI prompt - waiting for one wedges the port. This fires the command and returns immediately; follow with flipper_screenshot to see the app, and flipper_navigate to drive it. Find paths with flipper_storage_list.

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": {
      "fap_path": "<fap_path>"
    },
    "name": "flipper_launch_fap"
  }
}

Input Schema

NameRequiredDescriptionDefault
fap_pathYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), it discloses the key operational trait: it fires the command and returns immediately, a GUI app never yields a CLI prompt, and waiting wedges the port. That is exactly the non-obvious hazard an agent needs to know for a non-idempotent launch.

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?

Every sentence carries load: purpose and example first, then the sibling/listing caveat, then the critical no-prompt warning, then the recommended follow-up chain. There is no repetition of the schema or restating of the tool name.

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 a one-parameter launch tool with an output schema available, the description covers everything an agent must know to call it safely: input format, where to get valid values, return behavior (immediate return, no prompt), and the follow-up tools. Nothing material is left unstated.

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 description coverage is 0% for the single fap_path parameter, and the description compensates well by specifying the full SD path format with a literal example ('/ext/apps/GPIO/esp32_wifi_marauder.fap') and pointing to flipper_storage_list for discovery. It stops short of stating explicit validation rules (required .fap extension, leading-slash requirement), so it is strong but not exhaustive.

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 ('Launch an external .fap app') and immediately scopes it by input type ('by its full SD path'), with a concrete example path. It also distinguishes the resource class from built-ins ('External apps are NOT in `loader list`'), so an agent can separate this from loader/app-listing siblings without opening a schema.

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 an explicit conditional workflow: find the path with flipper_storage_list, launch here, then use flipper_screenshot to see the app and flipper_navigate to drive it. It also states a call-level rule ('do not wait for a CLI prompt') and names the alternatives for the follow-up actions, leaving little to inference.

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