Skip to main content
Glama

Export headless, check the build and run it

godot_export_run
Destructive

Export a Godot 4.7 preset headless and verify the result: compare the pack with what the game loads, then run the exported game to report runtime errors.

Instructions

Export a preset with Godot 4.7 headless and check the result instead of trusting it. mode pack (default; needs no templates), release or debug (need export templates), patch (only what changed: Godot's --export-patch against against base packs or the preset's patches, or cut from a full export by manifest, the base game's file list with md5, default godotwright.json baseFiles; it never ships an unchanged base file nor misses a changed one, and lists every file), or smoke (run an existing pck). Stops early on an unknown preset, a BOM in export_presets.cfg or missing templates; checks the file is there; compares the pack with what the game loads (missing files with their load chain, editor-only and test files shipped); runs the exported game headless for frames (default 120, 0 = none) and reports runtime errors with call chains. Writes to .godot/godotwright/export// unless out is given. An error result on any error.

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": "godot_export_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
outNooutput file inside the project (.pck for pack and patch)
pckNosmoke: the .pck or exported game to run
modeNodefault pack
pathNoproject folder, or a file or folder inside it (relative to the server's folder; default: the current project)
framesNoframes to run the exported game (default 120, 0 = no run)
presetNothe preset (name or number); not needed for smoke
againstNopatch: base .pck files in load order
manifestNopatch: lists of the base game's files (JSON with md5, or paths)
timeout_secondsNotimeout per Godot run (default 600)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real context beyond that: it names the default write location (.godot/godotwright/export/<preset>/), the early-abort conditions (unknown preset, BOM in export_presets.cfg, missing templates), the per-run timeout, and that any error yields an error result. It stops short of saying whether an existing output file at `out` is overwritten, which is the one destructive behavior an agent would want confirmed.

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?

The purpose is front-loaded in the first clause, but the body is a single dense run-on paragraph with stacked parentheses and semicolons — the patch-mode sentence in particular is one long tangle that must be re-read. Nearly every clause carries information, yet the lack of any structural break hurts scanability.

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 9 parameters, no output schema, and destructive side effects, the description does the heavy lifting well: it covers inputs' consequences, where output lands, what validation runs (file presence, pack-vs-load comparison, missing-file load chains, editor-only files shipped, headless run with runtime error call chains), and error signaling. Only the overwrite behavior and the exact result shape remain implicit.

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 meaning the schema does not: default mode semantics and template requirements per mode, frames=0 meaning no run, preset being unnecessary for smoke, and the precise meaning of `against`/`manifest` for patch including the default godotwright.json baseFiles. That is substantive semantics beyond the field descriptions.

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 definition names a specific verb and resource chain — export a preset headless with Godot 4.7, verify the resulting pack against what the game loads, then run the exported game for N frames. The five modes (pack/release/debug/patch/smoke) and the output location are spelled out, so an agent can tell this apart from a plain `godot_export` sibling without opening the 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?

Mode selection is genuinely guided: pack is the default and needs no templates, release/debug need export templates, patch only ships changed files, smoke runs an existing pck. What is missing is any explicit routing against sibling tools such as godot_export, godot_play, or godot_game, so the agent must infer when this tool beats those.

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