Skip to main content
Glama

capture_renderdoc_frame

Trigger a RenderDoc frame capture in the O3DE editor to diagnose rendering issues. Returns status indicating success, failure, or when manual capture is required.

Instructions

Trigger a RenderDoc frame capture in the O3DE editor.

Attempts to trigger a RenderDoc capture via GraphicsProfilerBus (reflected in the BehaviorContext but not exposed as a Python bus function in O3DE 2.7.0). If the bus call is not available, reports the limitation and suggests manual alternatives.

Returns: JSON with status ok if the capture was triggered, error on failure, or manual_required if the Python API cannot trigger the capture and manual action is needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

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 transparently states that the bus call may not be available, reports a fallback 'manual_required' status, and indicates the possible JSON statuses. This goes beyond a simple 'captures a frame' statement and prepares the agent for failure without being overly verbose.

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?

The description is front-loaded with the core purpose, then explains the technical mechanism and limitation, and ends with return statuses. Each sentence serves a purpose, though the middle paragraph about BehaviorContext and O3DE 2.7.0 is somewhat technical and could be trimmed without losing essential meaning.

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?

For a zero-parameter tool, the description is complete: it states what it does, how it attempts it, what can go wrong, and what the return values mean. The output schema exists and the Returns section aligns with it. A minor gap is the lack of prerequisites such as 'RenderDoc must be installed and configured,' but this is not critical for a basic call.

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 zero parameters and the schema is empty, so there are no parameter semantics to document. The description correctly focuses on behavior and return statuses rather than inventing parameter details. This meets the baseline expectation for a no-parameter tool.

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 opens with a specific verb and resource: 'Trigger a RenderDoc frame capture in the O3DE editor.' This clearly distinguishes it from sibling tools like capture_viewport, which captures a viewport image, and run_editor_python, which is a general-purpose execution tool. The purpose is unambiguous and immediately actionable.

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?

The description explains that the tool attempts to trigger a capture via the GraphicsProfilerBus and covers the failure case where the bus is not available in O3DE 2.7.0, suggesting manual alternatives. It does not explicitly name which alternative tool to use instead, but since no sibling tool is a direct substitute, the guidance is sufficient.

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