Skip to main content
Glama

connect_app

Launch or attach to the FilmCraft desktop app in control mode to edit projects live, with every change appearing in the app window and persisted via save_project.

Instructions

Drive the FilmCraft desktop app live: every edit then shows in its window as it happens. Launches a new FilmCraft window in control mode (an already open window is left alone), or attaches to one started with --control PORT and FILMCRAFT_CONTROL_TOKEN. While connected, tools without project, or with the project the app has open, edit the app; save with save_project.

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": "connect_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
openNoA .fcproj to open in the app once connected
portNo
tokenNoControl token of an app you started yourself (default: $FILMCRAFT_CONTROL_TOKEN, or a fresh one)
launchNoStart the app if nothing answers on the port

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and openWorldHint=false; the description adds real behavioral context on top of that — a GUI process is launched, existing windows are not displaced, attachment needs port and token, and the connection changes the routing of other tools (those without `project` edit the app). It does not cover failure behavior when nothing answers and launch is false, or whether the connection survives across calls.

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?

Three sentences, front-loaded with the core purpose before the launch/attach variants and the routing rule. Dense but every clause carries information; only the parenthetical about existing windows could be tightened.

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 stateful, no-required-param connection tool with no output schema, the definition covers launch, attach, credentials, and how the connection alters sibling-tool behavior. The remaining gaps — connection lifetime and the no-app-on-port case — are small but real for a tool whose whole job is session state.

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 75%, so the baseline is already near 3 from structured fields alone. The description contributes the meaning of the token source (--control / FILMCRAFT_CONTROL_TOKEN) and the port's attach role, but never mentions the `open` parameter, so it adds only partial meaning beyond the schema.

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?

"Drive the FilmCraft desktop app live: every edit then shows in its window as it happens" states a specific verb and resource, and the two modes (launch a new window vs. attach to one started with --control PORT) make the tool's identity unmistakable. It also names save_project as the follow-up, which further separates it from the edit-tool siblings.

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?

It gives a clear condition for use (when you want edits mirrored in the running app) and a key selection rule: an already-open window is left alone, and attaching requires --control PORT plus FILMCRAFT_CONTROL_TOKEN. It stops short of naming alternatives such as app_status or disconnect_app, so an agent must infer the pre-check and teardown tools on its own.

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