Create live source (input layer)

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

Annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) are supplemented by warnings about camera hanging on macOS, platform gating for NDI/Syphon/Spout, and defensive probing of source names. This adds valuable context beyond the structured annotations.

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 paragraph, front-loaded with the main purpose, and each sentence adds value (e.g., warnings, platform info). It could be slightly more concise or structured with bullets, but it is efficient and clear for an AI agent.

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?

Given the tool's complexity (multiple source kinds, platform gates), the description covers purpose, output, warnings, and per-kind behavior. It does not address error handling or side effects on existing nodes, but the output schema is absent, so return value explanation is not required.

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?

Schema description coverage is 100%, and the description adds extra meaning: it explains the safety of screen_grab, the permission issue with camera, and the behavior of source_name across kinds. The resolution parameter is adequately described in both schema and description.

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 clearly states the tool builds a source COMP for ingesting external feeds (screen grab, NDI, etc.) and exposes a Null TOP output. It distinguishes itself from sibling tools like create_video_player by focusing on live input and specifying the output's role in the pipeline.

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 explicit guidance on when to use each source kind: screen_grab is safe for testing, camera is opt-in with macOS permission risk, and others have platform/license requirements. It implicitly excludes other tools but does not name specific alternatives, leaving room for improvement.

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