Roblox BedWars Creative Scripting Tool MCP

Overview Schema Source Related Servers Discussions Admin

force_sync_directory

Prepare project files, optionally write a visible probe, then upload and retain a Code Sync connection for explicit first-sync troubleshooting.

Instructions

Prepare project files, optionally write a visible probe, then upload and retain a Code Sync connection. Inputs: sync_token (required string); directory (required string, project root path); glob_pattern (optional string, default empty: bwconfig.lua syncGlob or scripts/**/*.lua); probe (optional boolean, default true); probe_message (optional string, default empty: generated message); watch (optional boolean, default true: auto-upload later matching changes). Effects: creates scripts/, drafts/, and prompts/, creates main.lua if missing, writes project metadata and the brief, creates bwconfig.lua if missing, and writes or replaces scripts/zz_sync_probe.lua when probe=true. Uploads selected files and on success replaces the in-memory connection and applies watch. Returns preparation details, probe details, upload status, and connection/watcher flags.

Context: Choose only for explicit first-sync troubleshooting when project preparation or a visible in-game message is wanted. It uses the same upload transport as sync_directory, not a stronger remote-state check. It changes local project files even with probe=false; use sync_directory for normal existing-file uploads. Existing main.lua is preserved; the brief and metadata can be replaced. A custom glob must include the generated files to upload them. There is no allow_empty input; it does not offer delete-all. It cannot start a match or read the editor/console.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`probe`	No
`watch`	No
`directory`	Yes
`sync_token`	Yes
`glob_pattern`	No
`probe_message`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 2, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it enumerates every file/directory created or replaced, warns that local files change even with probe=false, notes main.lua is preserved while brief/metadata may be replaced, and states the in-memory connection is swapped and watch applied on success. It also lists negative capabilities (no allow_empty, no delete-all, cannot start a match or read the console).

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?

Well front-loaded with labeled Inputs/Effects/Returns/Context sections, and every sentence carries information. It is dense and somewhat long, but virtually nothing is filler given the zero schema coverage.

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

Completeness5/5

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

Output schema exists so return values need not be detailed, and the description still summarizes them. For a six-parameter mutation tool with no annotations and no schema descriptions, all the information an agent needs to invoke it safely is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (only titles), so the description must compensate and does: each of the six parameters is documented with required/optional status, defaults, and meaning (e.g. glob_pattern default source, probe_message generated when empty, watch semantics). The custom-glob caveat ('must include the generated files') adds behavior beyond the type.

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 first sentence names a specific verb chain (prepare files, write probe, upload, retain connection) applied to a directory, and the Context section explicitly differentiates it from sync_directory as a first-sync troubleshooting tool rather than a normal uploader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to choose it ('only for explicit first-sync troubleshooting when project preparation or a visible in-game message is wanted') and when not to ('use sync_directory for normal existing-file uploads'), and clarifies it is not a stronger remote-state check.

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

Deploy Server