inspect_previs_scene

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

With no annotations, the description carries the burden and does well: it states the work happens in background Blender against the project's verified target, that no scene is saved or rendered, and that any change to scene, dependency, playblast or inspection configuration creates a new revision and invalidates prior approvals. It omits error behavior and whether the run can be long-running or needs specific auth.

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?

Front-loads the core action in the first sentence and keeps the whole thing to four compact sentences. The third and fourth sentences are information-dense but earn their place; only the enumeration of collected data is slightly run-on.

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 six-parameter inspection tool with no annotations and no output schema, the description covers the read-only nature and revision side effects well but leaves parameter meanings and any hint of return shape or failure modes undocumented. It is adequate to start but not 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?

Schema coverage is 0%, so the description must compensate and it only partly does: 'Default samples: first/middle/last frame' explains the frames parameter, and 'distances from contact objects to the ground' implicitly covers contact_objects and ground_object. The collision_objects and playblast_path parameters receive no explanation, leaving meaningful gaps.

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?

Opens with a specific verb and resource: reads the saved .blend in background Blender and enumerates exactly what it collects (cameras, object scale, keyframes, evaluated transforms, intersections, ground distances). It is clearly not a mutation or audit tool, though it never explicitly distinguishes itself from siblings like audit_camera or audit_action.

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?

Implies usage via the default sampling behavior (first/middle/last frame) and warns that contact/intersection findings require human interpretation, which hints at the tool's verification role. However, there is no explicit when-to-use statement, no exclusions, and no pointer to an alternative sibling for related checks.

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