Create external I/O

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

With annotations only stating readOnlyHint=false, openWorldHint=true, destructiveHint=false, the description adds substantial behavioral context: platform constraints (RTMP requires NVIDIA GPU on Windows; Spout needs NVIDIA/AMD but not Intel), default safety behaviors (active defaults off so the artist can confirm destination), error tolerance for bind_to (missing channels fall back to 0), and validation limitations. This goes well beyond the annotations and gives the agent critical operational expectations.

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 a single dense paragraph with lengthy parenthetical asides and repetitive enumerations. It is front-loaded with the core purpose, but the structure makes it harder to scan. While every part is informative, it could be organized with bullets or separate sections for input vs output categories to improve readability without losing content.

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?

The description covers all major categories, platform-specific requirements, default behaviors, validation caveats, and an alternative tool usage (get_td_nodes). There is no output schema, so return-value documentation is not required. For a tool with 17 parameters and 15 kind variants, this description is remarkably complete, leaving few ambiguities about how and when to invoke it.

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?

While the schema already describes all 17 parameters (100% coverage), the description enriches their semantics significantly. It explains workflows like passing source_path for outputs, using bind_to with learned channels from get_td_nodes, and the distinction between dmx_out and artnet_out via the net/interface parameters. The prose adds conceptual meaning and practical usage guidance that the schema's per-parameter descriptions do not fully convey.

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 explicitly states 'Bridge TouchDesigner to the outside world' and enumerates the full spectrum of supported I/O kinds (OSC/MIDI input/output, DMX/Art-Net, RTMP, NDI/Syphon-Spout). This clearly distinguishes it from sibling tools like create_control_surface or create_ndi_router_matrix by framing it as a generic external I/O bridge. The verb 'bridge' and the detailed resource list make the purpose unmistakable.

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 description provides clear when-to-use context, covering all the I/O bridging scenarios. It explicitly names an alternative workflow for discovering MIDI channels ('use get_td_nodes, then bind_to'), and warns about validation limits ('real signal needs the hardware/sender present'). However, it doesn't explicitly contrast with sibling tools beyond that one example, so it falls just short of a 5.

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