fuast

Check an app without deploying

check_app

Read-onlyIdempotent

Builds the files, type checks them and loads the server in a sandbox, without deploying anything. Returns ok with the queries, mutations, tables and tools the app declares, or ok false with diagnostics that carry file, line and message. Call it before deploy_app and fix every diagnostic.

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": {
      "files": "<files>"
    },
    "name": "check_app"
  }
}

Input Schema

Name	Required	Description	Default
`files`	Yes	The whole app as {"relative/path": "file content"}. server/index.ts and client/index.tsx are required. Text files only (.ts .tsx .js .jsx .mjs .json .md .svg .txt .css .html).

Output Schema

Name	Required	Description	Default
`ms`	No
`ok`	Yes
`code`	No
`name`	No
`error`	No
`sizes`	No
`manifest`	No
`warnings`	No
`diagnostics`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and closed-world safety, and the description adds real value on top: sandboxed execution with no deployment side effect, and the two outcome modes (ok with declared capabilities, or ok=false with file/line/message diagnostics). The return shape overlaps the output schema, so it is strong but not maximally additive.

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?

Three short sentences, front-loaded with the purpose and the no-deploy guarantee, then the return contract, then the workflow instruction. No filler and nothing repeated.

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?

Complete enough for a one-parameter tool with full schema coverage and an output schema. The description covers purpose, safety, failure diagnostics, and sequencing. Only minor gaps remain, such as whether checking consumes limits or how large an app may be.

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?

The single files parameter has 100% schema description coverage, including required entry points and allowed extensions, so the schema already does the explanatory work. The description only refers to "the files" generically and adds no meaning beyond it. Baseline 3 applies.

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 concrete verbs and a concrete resource: builds files, type checks, and loads the server in a sandbox without deploying. It explicitly frames itself against deploy_app, so an agent can separate it from the deployment siblings without reading either 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?

Gives a clear imperative sequencing rule: call it before deploy_app and fix every diagnostic. That establishes when to use it and the precondition for deployment. It does not name when-not to use it or alternatives such as inspect_app, so it falls short of the full 5.

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

All fuast tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?