Create live source (input layer)

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses critical runtime behaviors: camera can hang TouchDesigner on a macOS permission modal, NDI requires runtime, Syphon/Spout are OS-specific, and par names are probed defensively turning build differences into warnings. This is substantial behavioral context that annotations alone do not provide.

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?

Three sentences, each earning its place: the first states the core build action and output, the second covers safety/permission/platform caveats, and the third explains defensive probing. Dense but not bloated, and front-loaded with the most important information.

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?

Despite no output schema, the description states the output clearly ('exposes a named Null TOP output'). It accounts for all 5 parameters, platform quirks, permission risks, and defensive behavior. For a creation tool with zero required parameters, this is exceptionally complete.

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?

Input schema covers 100% of parameters, so the baseline is 3. The description adds extra meaning by linking `source_name` to all source kinds and explaining defensive probing of par names, which clarifies how the parameter behaves in different TD builds. It also frames `resolution` as part of a Fit/Resolution stage, adding context beyond the schema.

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 opens with a specific verb+resource: 'Build a self-contained source COMP that ingests an external feed...' and enumerates exact source kinds (screen grab, NDI, Syphon/Spout, camera, video stream). It clearly distinguishes this tool from generic create_* tools by emphasizing the input-layer role and the Null TOP output.

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?

It provides explicit guidance on when to use each `kind` value (e.g., screen_grab is safe for testing, camera can hang on macOS, NDI/Syphon/Spout are platform-gated). However, it does not name alternative sibling tools or state conditions where this tool should not be used, so it stops short of full exclusions/alternatives.

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