Skip to main content
Glama

import_file

Uploads a local file to your Roblox account and inserts it into the open place as a Model, Sound, or Decal; supports model, audio, and image files.

Instructions

Import a LOCAL file into Roblox: uploads it to the user's own account via the Open Cloud Assets API (needs TUFAN_OPENCLOUD_KEY), then inserts it into the open place. Supports .rbxm/.rbxmx/.fbx/.gltf/.glb (Model), .mp3/.ogg/.wav/.flac (Audio → Sound instance; wav/flac acceptance may vary), .png/.jpg/.bmp/.tga (Decal instance). NOT .obj — convert to .fbx/.glb first. Max 20 MB. Audio uploads are quota-limited (10/month, 100/month if ID-verified) and queue for moderation — they often outlive waitSeconds; when that happens the call returns an operationId, and re-calling with { operationId } resumes WITHOUT re-uploading or burning quota. Models typically finish in seconds. For an EXISTING marketplace asset by id, use insert_asset instead; to AI-generate a new mesh from a prompt/image, use generate_asset instead.

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": "import_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDisplay name on Roblox (default: file name)
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
anchorNoAnchor all parts after a Model insert (opt-in)
insertNoInsert into the place after upload (default true)
filePathNoAbsolute path of the local file to upload
onGroundNoDrop the inserted Model flush onto whatever is below it (opt-in)
positionNo[x,y,z] world position for the inserted Model's pivot (opt-in)
assetTypeNoOverride auto-detect — e.g. Animation for a KeyframeSequence .rbxm
parentPathNoWhere to insert in the place (default Workspace)
descriptionNoDescription shown on the asset's Roblox page. Default empty.
operationIdNoResume a pending upload instead of uploading again
waitSecondsNoMax seconds to wait for Roblox-side processing after upload (default 45, max 240)
collisionFidelityNoSet on every MeshPart after a Model insert (opt-in; Hull = cheap static-prop choice)
targetHeightStudsNoScale the inserted Model so its height equals this many studs (opt-in)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / description / description
      Added value: +"Description shown on the asset's Roblox page. Default empty."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare the safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false, idempotentHint=false); the description adds substantial undisclosed behavior: an API key requirement, a 20 MB cap, per-month audio quotas tied to ID verification, moderation queuing, and the fact that audio often outlives waitSeconds while models finish in seconds. It does not say what a successful non-deferred call returns (asset id, instance path), which is the one behavioral gap left.

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?

Front-loaded with the core action and target, then formats, then limits, then the resume behavior, then sibling routing — a sensible information hierarchy with no filler sentences. It is dense for a single description, but each clause (size cap, quota numbers, .obj exclusion) is operationally load-bearing rather than decorative.

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?

For a 14-parameter mutation tool with no output schema, the description covers the authentication prerequisite, size and format constraints, quota limits, the deferred-operation return value, and the alternative tools. An agent has enough to choose the tool, pick a format, and handle the async case without further discovery.

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 schema already carries per-parameter meaning and the baseline is 3. The description still adds real semantics the schema cannot: it explains the operationId resume contract (no re-upload, no quota burn) and the practical interaction between waitSeconds and moderation delay, which changes how an agent should set that parameter.

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 a specific verb and resource ('Import a LOCAL file into Roblox: uploads it to the user's own account via the Open Cloud Assets API ... then inserts it into the open place'), naming both the upload and insert phases. It also explicitly separates itself from insert_asset (existing marketplace asset) and generate_asset (AI-generated mesh), so an agent can route correctly without opening another schema.

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?

Gives explicit when-to-use routing ('For an EXISTING marketplace asset by id, use insert_asset instead; to AI-generate a new mesh ... use generate_asset instead') and a hard exclusion ('NOT .obj — convert to .fbx/.glb first'). It also documents the resume path ('re-calling with { operationId } resumes WITHOUT re-uploading or burning quota'), which is the key decision point for a retry.

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