Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

up

Starts the app stack or selected services detached, then reports whether they are ready, starting, failed or timed out. Use it to launch a project and confirm service readiness.

Instructions

Start the stack (or part of it) detached from the optional projectPath. The result carries state: ready (every local-process service passed its readiness check), starting (launched, readiness not confirmed: the default after a short wait; poll status, or pass waitForReady), failed (a service exited or gave up; the error carries its own output) or timeout (waitForReady was set and readiness was not reached in waitSeconds; it keeps starting). started: true never means ready. Fails fast on an unknown service, an unsupported host, or a Tilt already running.

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": "up"
  }
}

Input Schema

NameRequiredDescriptionDefault
onlyNoStart only these services plus what they depend on and shared infrastructure
forceNoReplace a Tilt that is already running
stackNoOnly this stack
dryRunNoShow what would be started without starting
projectPathNoAbsolute path to the Flisk project root; run this operation from that directory.
waitSecondsNoHow long to wait before returning (default 15, max 60; with waitForReady default 120, max 600)
waitForReadyNoWait until every service passed its readiness check (local-process stacks), instead of only watching for an early failure

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.69
    • addedInput schema / properties / waitForReady
      Added value: +{
      +  "description": "Wait until every service passed its readiness check (local-process stacks), instead of only watching for an early failure",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / waitSeconds / description
      Previous value: -"How long to watch for an early failure before returning (default 15, max 60)"New value: +"How long to wait before returning (default 15, max 60; with waitForReady default 120, max 600)"
  2. First observedv1.4.17

TDQS

A4.3/5.0
Behavior5/5

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

Goes well past the annotations (which only say non-read-only, non-destructive, closed-world) by enumerating the `state` outcomes with their exact meanings, including that `timeout` keeps starting in the background. The explicit warning that '`started: true` never means ready' and that a `failed` error carries its own output are exactly the behavioral facts an agent would otherwise get wrong.

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?

Front-loads what the tool does, then spends the remainder on return-state semantics — the highest-risk information. Dense parentheticals but no sentence is filler; every clause either defines a state or a failure mode.

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?

With no output schema, the description correctly takes on the burden of explaining the returned `state` values and the `started` flag. It leaves the `force`/already-running interplay and multi-stack behavior thin, but an agent has enough to call it correctly and interpret the result.

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 semantics the schema cannot: `waitForReady` interacts with `waitSeconds` to produce the `timeout` state, and that state is non-terminal. It does not clarify `only`, `stack`, `force`, or `dryRun` beyond what the schema already says, which caps it at 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Start the stack (or part of it)') and scopes it to a project path, which is enough to distinguish it from siblings like `down` or `status`. The phrase 'detached from the optional projectPath' is grammatically muddy and slows parsing of the scope claim, keeping it below a 5.

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?

Clear operational guidance: it names the `status` sibling to poll when the result is `starting`, and suggests passing `waitForReady` as the alternative when readiness matters. It also enumerates fail-fast conditions (unknown service, unsupported host, Tilt already running), but never states when NOT to use it or how `force` fits the already-running case.

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