Skip to main content
Glama

assets-delete

Remove unwanted assets from Unity projects by specifying their paths. Automatically refreshes the Asset Database after deletion to maintain project integrity.

Instructions

Delete the assets at paths from the project. Does AssetDatabase.Refresh() at the end. Use 'assets-find' tool to find assets before deleting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathsYesArray of asset paths to delete. Example: ["Assets/Materials/Mat.mat"]

Implementation Reference

  • The call_tool function in mcp_server.py handles the execution of any Unity Bridge tool, including 'assets-delete', by writing a JSON command file to a file IPC directory and waiting for a response file.
    def call_tool(name, arguments):
        """Execute a Unity Bridge tool via file IPC. Returns MCP content result."""
        bridge_dir = get_bridge_dir()
        commands_dir = os.path.join(bridge_dir, "commands")
        results_dir = os.path.join(bridge_dir, "results")
    
        # Heartbeat check
        err = check_heartbeat(bridge_dir)
        if err:
            return True, err
    
        # Write command
        command_id = f"{int(time.time())}-{uuid.uuid4().hex[:8]}"
        command = {"id": command_id, "tool": name, "params": arguments or {}}
    
        os.makedirs(commands_dir, exist_ok=True)
        os.makedirs(results_dir, exist_ok=True)
    
        command_file = os.path.join(commands_dir, f"{command_id}.json")
        write_atomic(command_file, json.dumps(command))
    
        # Poll for result
        result_file = os.path.join(results_dir, f"{command_id}.json")
        elapsed = 0.0
    
        while not os.path.exists(result_file):
            time.sleep(IPC_POLL_INTERVAL)
            elapsed += IPC_POLL_INTERVAL
            if elapsed >= IPC_TIMEOUT:
                try:
                    os.remove(command_file)
                except OSError:
                    pass
                return True, f"Timeout after {IPC_TIMEOUT}s waiting for Unity (tool: {name})"
    
        # Read result
        try:
            with open(result_file, "r", encoding="utf-8") as f:
                result = json.load(f)
        finally:
            try:
                os.remove(result_file)
            except OSError:
                pass
    
        is_error = result.get("status") != "success"
        message = result.get("message", "")
        return is_error, message
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool performs 'AssetDatabase.Refresh() at the end', which is valuable behavioral context about side effects. However, it doesn't mention critical details like whether deletion is permanent/reversible, permission requirements, error handling for invalid paths, or confirmation prompts. For a destructive operation with zero annotation coverage, this leaves significant gaps.

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?

The description is extremely concise with only two sentences, both of which earn their place. The first sentence states the core action and side effect, while the second provides crucial usage guidance. There is zero wasted verbiage or redundancy.

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?

For a destructive tool with no annotations and no output schema, the description does the minimum viable job: it states the purpose, mentions a side effect, and provides usage guidance. However, it lacks important context about the permanence of deletion, error conditions, or what happens to dependent assets. Given the high-stakes nature of deletion, more behavioral transparency would be warranted.

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?

Schema description coverage is 100%, with the schema clearly documenting the 'paths' parameter as an array of asset paths with an example. The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline score of 3 for high schema 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?

The description clearly states the specific action ('Delete') and target resource ('assets at paths from the project'), distinguishing it from sibling tools like 'assets-move' or 'assets-modify'. It also mentions the additional effect 'AssetDatabase.Refresh() at the end', which adds specificity beyond a basic delete operation.

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?

The description explicitly provides when-to-use guidance by stating 'Use 'assets-find' tool to find assets before deleting', naming a specific alternative tool for the prerequisite step. This clearly directs the agent to use a different tool first before invoking this one.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/butterlatte-zhang/unity-ai-bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server