Create live source (input layer)

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

Discloses important behavioral traits beyond annotations: camera can hang on macOS permission modal, NDI requires runtime, Syphon/Spout are platform-specific. Also mentions defensive probing of parameter names. No contradiction with annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true).

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?

Single dense paragraph front-loaded with purpose. Every sentence adds value (warnings, platform details). Could benefit from slight restructuring for clarity, but remains efficiently informative.

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 5 parameters, one enum, no output schema, the description covers all necessary context: warnings, platform limitations, safe defaults, and parameter behaviors. No gaps for agent execution.

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 coverage is 100%, but description adds context: explains default safety for 'kind', platform/license gating, and that 'source_name' probing is defensive. Provides richer meaning beyond schema descriptions.

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?

Description clearly states it builds a self-contained source COMP that ingests various external feeds, normalizes to target resolution, and exposes a Null TOP output. Distinguishes from siblings like create_video_player or create_data_source by specifying feed types and integration details.

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?

Provides clear guidance on when to use each kind: default screen_grab is safe, camera is opt-in with macOS permission modal, NDI/Syphon/Spout are platform/license-gated. Does not explicitly name alternative sibling tools but offers sufficient context for decision-making.

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