Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

resource_restart

Restart one running resource and its active sidecar containers without rebuilding, while leaving unrelated resources untouched. Requires a running stack; set rebuild to recreate the image.

Instructions

Restart one running resource in the stack along with any active container resources that transitively declare sidecarOf on it (Flisk-generated Compose containers restart without rebuilding their image; local-process resources of a project that runs without Tilt are restarted by the run that supervises them (its .env is re-read, only that service is stopped and started, and the result says whether it is ready, failed with its own output, or still starting); other non-container resources and projects using an imported Tiltfile fall back to tilt trigger); unrelated resources are not touched. It needs a running stack: start one with up. Set rebuild to true for a full Tilt update (rebuild the image and recreate the container, which re-reads the project .env). Names come from resource_list. 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": "resource_restart"
  }
}

Input Schema

NameRequiredDescriptionDefault
rebuildNoRebuild the image and recreate the container through Tilt
resourceNoName of the resource to restart
projectPathNoAbsolute path to the Flisk project root; run this operation from that directory.
waitSecondsNoLocal-process stacks: how long to wait for the service to be ready again (default 60, max 300; 0 returns once the restart has begun)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.69
    • addedInput schema / properties / rebuild
      Added value: +{
      +  "description": "Rebuild the image and recreate the container through Tilt",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / waitSeconds
      Added value: +{
      +  "description": "Local-process stacks: how long to wait for the service to be ready again (default 60, max 300; 0 returns once the restart has begun)",
      +  "type": "number"
      +}
  2. First observedv1.4.17

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare this a non-read-only, non-destructive, closed-world mutation, so the safety bar is lower. The description still adds real behavior beyond them: sidecar propagation, per-strategy restart mechanics (.env re-read, only that service stopped/started), and the ready/failed/still-starting result states. A 3 here reflects that the highest-value gaps remain — no mention of what happens to in-flight requests during the stop/start window, and no docs on `waitSeconds` behavior from the description side.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Front-loaded with the core action and scope, and nearly every clause carries real information. But it is one sprawling sentence with parentheticals nested inside parentheticals, which forces re-reading to parse the three restart strategies.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a 4-parameter mutation with no output schema, the description covers prerequisites, dispatch variants, and result states well. Still, `waitSeconds` and its interaction with the local-process path are not integrated into the narrative, so the timing story is split between prose and schema.

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 baseline would be 3; the description earns above baseline by explaining that `rebuild` recreates the image and re-reads the project .env, and that `projectPath` is needed only when the MCP server isn't at the project root. `waitSeconds` is left entirely to the schema, which is acceptable given its coverage.

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 the specific verb and resource ('Restart one running resource') and immediately bounds the blast radius: sidecar-declaring container resources come along, 'unrelated resources are not touched.' The three dispatch paths (Flisk-generated Compose, local-process, tilt trigger fallback) make it unmistakable versus siblings like `up` or `resource_run`.

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?

Explicit prerequisite: 'It needs a running stack: start one with `up`,' plus routing to `resource_list` for names and to `rebuild` for the full-update path. It also names the fallback path for Tiltfile projects. What's missing is a direct contrast with a sibling such as `resource_run` or a statement of when not to restart.

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