scene_inspectInspect scene layout at selected preview times without rendering video, so you can verify composition and catch layout issues before full renders.
Inspect layout at preview frames without rendering video.
| Name | Required | Description | Default |
|---|---|---|---|
| times | No | ||
| scene_id | Yes | ||
| project_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| issues | No | ||
| stderr | Yes | ||
| stdout | Yes | ||
| exit_code | Yes | ||
| duration_seconds | No | ||
| storyboard_paths | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden, yet it does disclose one non-obvious trait: no video is produced, so the agent knows this is a cheap inspection path rather than an expensive render. It says nothing about whether frames or files are written to disk, permissions, or cost, which for an unannotated tool is a real gap.
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?
A single front-loaded sentence with zero waste; the differentiator is placed immediately. It is arguably too terse for a three-parameter tool, but nothing in it is padding.
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?
An output schema exists, so return values need not be described, but with zero annotation coverage and 0% schema coverage the description leaves the `times` semantics and the disk/IO side effects unexplained. For a tool sitting among many scene_* siblings, that is under-specified.
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 0% and none of the three parameters are explained. The mention of 'preview frames' faintly hints at the `times` parameter, but nothing states that it takes numeric timestamps or the literal 'end', nor what 'end' resolves to.
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?
States a specific verb (inspect) and object (layout at preview frames), and the clause 'without rendering video' separates it from scene_render_preview and scene_render_final. What 'layout' concretely covers is left vague, but the operation is identifiable.
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 phrase 'without rendering video' implies you should use this instead of a render tool when you only need a check, but no sibling is named and no when-not condition is stated explicitly. Usage must be inferred from the negation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.