Skip to main content
Glama

renderdoc_get_capture_info

Retrieve detailed information about an open RenderDoc capture, including API, driver, and resource counts for graphics debugging.

Instructions

Get detailed information about the currently open capture including API, driver, and resource counts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The handler for 'renderdoc_get_capture_info' tool that checks if a capture is open and retrieves capture information using the wrapper's _get_capture_info() method, then formats the output for display.
    elif name == "renderdoc_get_capture_info":
        if not wrapper.current_file:
            return [TextContent(type="text", text="Error: No capture is currently open. Use renderdoc_open_capture first.")]
    
        info = wrapper._get_capture_info() if not wrapper._use_fallback else None
        if info:
            return [TextContent(type="text", text=_format_capture_info(info))]
        return [TextContent(type="text", text="Error: Unable to get capture info.")]
  • Tool registration defining 'renderdoc_get_capture_info' with its name, description, and input schema (no required parameters).
    Tool(
        name="renderdoc_get_capture_info",
        description="Get detailed information about the currently open capture including API, driver, and resource counts.",
        inputSchema={
            "type": "object",
            "properties": {},
            "required": [],
        },
    ),
  • The _get_capture_info() helper method that implements the actual RenderDoc API calls to retrieve capture details including API properties, resource counts, and frame information.
    def _get_capture_info(self) -> CaptureInfo:
        """Get capture information using native API."""
        if not self.controller:
            raise RuntimeError("No capture is currently open")
    
        # Get API properties
        api_props = self.controller.GetAPIProperties()
        driver_name = api_props.pipelineType
    
        # Map pipeline type to API name
        api_type_map = {
            rd.GraphicsAPI.D3D11: "D3D11",
            rd.GraphicsAPI.D3D12: "D3D12",
            rd.GraphicsAPI.Vulkan: "Vulkan",
            rd.GraphicsAPI.OpenGL: "OpenGL",
            rd.GraphicsAPI.OpenGLES: "OpenGLES",
            rd.GraphicsAPI.Metal: "Metal",
        }
        api_type = api_type_map.get(driver_name, "Unknown")
    
        # Count resources
        textures = self.controller.GetTextures()
        buffers = self.controller.GetBuffers()
    
        # Count draw calls in frame
        frame_info = self.controller.GetFrameInfo()
        draw_call_count = len(frame_info.drawcalls) if hasattr(frame_info, 'drawcalls') else 0
    
        return CaptureInfo(
            file_path=self.current_file or "",
            driver_name=api_props.localRenderer or "Unknown",
            api_type=api_type,
            machine_ident=api_props.machineIdent if hasattr(api_props, 'machineIdent') else None,
            frame_count=1,
            draw_call_count=draw_call_count,
            texture_count=len(textures),
            buffer_count=len(buffers),
        )
  • The _format_capture_info() helper function that formats the CaptureInfo dataclass into a human-readable text output with file path, API type, driver info, and resource counts.
    def _format_capture_info(info: CaptureInfo) -> str:
        """Format capture info for display."""
        return f"""Capture Information:
    - File: {info.file_path}
    - API: {info.api_type}
    - Driver: {info.driver_name}
    - Machine ID: {info.machine_ident or 'N/A'}
    - Frame Count: {info.frame_count}
    - Draw Calls: {info.draw_call_count}
    - Textures: {info.texture_count}
    - Buffers: {info.buffer_count}"""
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what information is retrieved but lacks details on behavioral traits such as whether this is a read-only operation (implied by 'Get'), potential errors if no capture is open, performance characteristics, or output format. This leaves significant gaps for a tool with no annotation coverage.

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 a single, well-structured sentence that efficiently conveys the tool's purpose and scope ('detailed information about the currently open capture') with specific examples ('API, driver, and resource counts'). It is front-loaded with the core action and avoids any redundant or extraneous information.

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?

Given the tool has 0 parameters, no annotations, and no output schema, the description provides basic purpose and context but is incomplete for effective use. It doesn't explain the return values or format, error conditions, or dependencies on other tools (e.g., requiring an open capture). For a tool with no structured data support, more behavioral and output details would improve completeness.

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?

The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics beyond the schema, and it appropriately focuses on the tool's purpose without unnecessary parameter details, earning a baseline score of 4 for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('detailed information about the currently open capture'), including what information is retrieved (API, driver, and resource counts). However, it doesn't explicitly differentiate from sibling tools like 'renderdoc_get_buffers' or 'renderdoc_get_textures' that also retrieve specific types of capture information, so it falls short of a perfect score.

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

Usage Guidelines3/5

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

The description implies usage context by specifying 'currently open capture', suggesting this tool should be used after a capture is opened (e.g., via 'renderdoc_open_capture'). However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'renderdoc_get_buffers' for buffer-specific data or 'renderdoc_get_draw_calls' for draw call details, nor does it mention prerequisites or exclusions.

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/Hengle/Renderdoc-Mcp2'

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