omniverse-mcp

Overview Schema Source Related Servers Discussions Admin

inspect_prim

Capture screenshots from up to 14 fixed angles around a USD prim, with auto-fitted camera distance, optional isolation and segmentation, to visually inspect geometry from every side.

Instructions

Orbit-capture: take screenshots from 14 systematic angles around a prim (cube-based).

    Auto-fits camera distance so the prim fills the viewport with ~10px margin.
    Captures from all 6 face centers + 8 cube corners by default, giving full coverage.
    Saves each angle as a PNG file. Use Read tool to view images.

Input Schema

Name	Required	Description
`width`	No	Image width in pixels
`angles`	No	Angle names, all 14 when omitted. Face centres: "front", "back", "right", "left", "top", "bottom". Cube corners: "top_front_right", "top_front_left", "top_back_right", "top_back_left", "bottom_front_right", "bottom_front_left", "bottom_back_right", "bottom_back_left"
`height`	No	Image height in pixels
`isolate`	No	Hide everything else while capturing, then restore it
`prim_path`	Yes	Full USD path of the prim, e.g. "/World/Robot"
`zoom_offset`	No	Adjusts the fitted distance: negative closer, positive further (-0.3 is 30% closer)
`include_segmentation`	No	Also capture instance segmentation at each angle

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.2Oct 29, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Goes beyond the annotations by disclosing that PNG files are written to disk (explaining why readOnlyHint is false despite being nominally a capture), that the camera is auto-fitted with a ~10px margin, and that isolate temporarily hides and then restores other objects. It stops short of stating where files are saved or how they are named.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core action and followed by the key behavioral facts (auto-fit, coverage, file output, Read hint). No filler, though the awkward line breaks and indentation slightly hurt scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and all 7 parameters documented, the description covers behavior adequately. The one real gap is the output file location/naming convention, which the agent needs in order to actually Read the PNGs it just produced.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter already carries its own description including the full angle-name list and zoom_offset semantics. The description adds only the confirming detail that all 14 angles are captured by default, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'take screenshots from 14 systematic angles around a prim', with the exact composition of those angles (6 face centres + 8 cube corners). This is clearly distinguishable from sibling tools like capture_viewport or look_at_prim, which do not imply multi-angle orbit capture.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (visual inspection of a prim) and the description adds a useful post-step hint ('Use Read tool to view images'), but it never states when to choose this over capture_viewport, look_at_prim, or compare_prims. No exclusions or alternatives are named.

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