vmix_scene_create

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

The description adds valuable behavioral details beyond the annotations: 'Never removes inputs on failure' provides a safety guarantee that is not implied by destructiveHint=true, and 'Pixel coordinates are based on the vMix preset resolution' clarifies a technical aspect of the input coordinates. This goes beyond what annotations convey, though it does not describe the full mutation effect on the vMix state.

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 long, with the primary purpose front-loaded and no redundant filler. Every clause adds information: the scene type, the layer capacity, the geometry options, and the coordinate system. It is an excellent model of brevity.

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 five parameters and a nested array schema, the description gives enough context to understand the core function but omits key operational details like the role of dry_run and request_id. The absence of an output schema and lack of parameter explanations mean an agent may need to guess at some aspects, so it is only moderately 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?

With schema description coverage at 0%, the description must compensate by explaining parameters. It does mention 'layers', 'pixel rectangles and crop', and hints at the background via 'colour-backed', but it does not explain 'dry_run', 'request_id', or the exact structure of the layers array beyond the schema. Several parameters remain undocumented in plain language, so the description only partially compensates.

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 action ('Build') and the resource ('off-air colour-backed scene') with specifics like 'up to 10 layers, pixel rectangles and crop'. It is unambiguous about what the tool does. However, it does not explicitly differentiate from sibling tools like vmix_scene_template, so it earns a 4 rather than a 5.

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 gives no explicit guidance on when to use this tool versus alternatives. It implies it is for off-air scenes (via the phrase 'off-air'), but it does not state exclusions or recommend sibling tools for other scenarios. This leaves the agent to infer usage from context alone.

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