Check GPU utilization and VRAM usage, and verify that TouchDesigner is actively rendering to detect stalled or unhealthy output.
GPU util/VRAM + whether TD is really rendering. The 'looks healthy but isn't' detector.
require_render (bool | None): Error if TD is not rendering (default true).
| Name | Required | Description | Default |
|---|---|---|---|
| require_render | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must disclose behavioral details. It does explain that require_render (default true) will error when TD is not rendering, which is a concrete behavior. It does not clarify whether this is a read-only operation, what output shape is produced, or whether any side effects exist, leaving some behavioral gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences of prose: the first conveys the tool's output and core purpose, the second addresses the sole parameter. There is no filler, no repetition of the tool name, and the most relevant information that appears first.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one optional parameter and no output schema, the description covers what the tool exports (GPU health and render status) and the parameter's semantic. It doesn't describe the return format, but that information is likely not required for a simple diagnostic. The 'detector' phrase gives extra context beyond the technical description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides no descriptions and only marks the parameter as an optional 'boolean or null' with a null default. The description adds meaning by stating that require_render controls the error behavior when TD is not rendering and clarifies the default effective value (true), which the agent could not deduce from the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description communicates that the tool measures GPU utilization/VRAM and whether TD is actually rendering, encapsulated as a 'looks healthy but isn't' detector. This distinguishes it from other measure_* siblings, but it lacks an explicit verb like 'measure' or 'get'; the tool name supplies the action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'the looks healthy but isn't detector' and the require_render parameter imply when it should be used: when other metrics suggest system health but real rendering may be failing. However, no explicit alternatives are named, and no clear 'use this instead of X' or 'don't use this when Y' conditions are provided, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.