Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

project_import

Destructive

Import services from a directory's docker-compose.yml into service.json files for a Flisk project, with dry-run previews and controlled overwrites when files already exist.

Instructions

Import the services in a directory's root docker-compose.yml as bring-your-own service.json files with flisk import --json, which runs the pinned flisk-import from npm (the first run needs network access). It writes without asking: set dryRun to get the plan only, and force to overwrite an existing service.json (force needs confirm: true unless dryRun is set). Returns data.written and the importer's output. Set projectPath when the MCP server is not running from the project root.

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": "project_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirNoDirectory with the docker-compose.yml, relative to projectPath or absolute (default: projectPath)
forceNoOverwrite an existing service.json
dryRunNoPrint the plan and write nothing
confirmNoMust be true together with force (unless dryRun) to overwrite files
projectPathNoAbsolute path to the Flisk project root; run this operation from that directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.69
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "Must be true together with force (unless dryRun) to overwrite files",
      +  "type": "boolean"
      +}
  2. First observedv1.4.17

TDQS

A4.5/5.0
Behavior5/5

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

The annotations already flag destructiveHint=true and openWorldHint=true, and the description adds substantial detail beyond them: it writes without asking, the first run pulls a pinned npm package and therefore needs network access, force is gated behind confirm unless dryRun is set, and it returns data.written plus the importer's output. That is exactly the kind of operational context annotations cannot carry.

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?

Four sentences, front-loaded with the core action, then the write-without-asking warning, then the guardrail flags, then the return value. Dense but nearly every clause carries information; the parenthetical about npm and network access could be trimmed slightly.

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, open-world import operation with five optional parameters and no output schema, the description covers the safety profile, prerequisites, and return shape well. Minor gaps remain, such as whether the target directory must already exist or what happens to other files in it.

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%, so the baseline is 3, but the description adds cross-parameter meaning the schema only partly states: the force/confirm/dryRun interaction and the conditional need for projectPath when the server is not rooted in the project. It does not explain `dir` defaults beyond what the schema already says.

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?

The description names a specific verb and resource combination ('Import the services in a directory's root docker-compose.yml as bring-your-own service.json files') and names the concrete command that runs, so an agent can distinguish this from project_init, project_eject, or resource_create without opening any 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?

It gives concrete operating conditions rather than vague hints: use dryRun when you only want the plan, set projectPath when the MCP server is not running from the project root. It does not explicitly exclude alternatives such as project_init, so it stays just 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.