3D New Era AI

Overview Schema Source Related Servers Discussions Admin

Inspect an imported model

model

Read-only

Inspect imported 3D files or placed pieces by ID to verify units, size, triangles, materials, named parts, warnings, and clashes before insertion.

Instructions

Inspect an imported 3D model, a piece's (id) or a file before placing it: the unit taken (guessed from its size unless unit= or the piece says), natural size, triangles and where they go, materials with their images, named parts (OBJ objects and groups, glTF nodes: arms, seat, frame) with bounds and materials, and warnings for what is not drawn as the file says (a texture or material library not found, normal and roughness maps, extensions). For a piece that looks wrong after place model=…, instead of reading the file. part= keeps the parts named so; check=clashes finds parts passing through one another (a cushion through a rail), not those that touch. Reply {file, format, unit, raw, size cm, tris, materials [[name, color, image, tris]], parts [[name, tris, min, max, materials, "hidden" when hidden]] in cm of the piece (x across, y to the front, z up), cost {tris, heaviest [[part, tris, %]], copies, in_project}, warnings}; with id also piece {size, scale, far}; check adds clashes [[part, part, pairs, at, depth cm]], degenerate and checked (what was looked at). place model=… imports one.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	A piece that uses an imported model, e.g. `f12`
`tol`	No	check: how far a surface must pass the other to count, cm (default 0.05); touching is not a clash
`file`	No	Instead of `id`: an .obj/.gltf/.glb file, before placing it
`part`	No	Only the parts whose name has these words (`braco`), all of them
`unit`	No	Unit of the file's numbers, `m`, `cm`, `mm` or `in` (default: the piece's, or guessed)
`check`	No	`clashes`: which parts pass through one another, and faces with no area

Output Schema

TableJSON Schema

Name	Required	Description	Default
`uv`	No
`raw`	No
`cost`	No
`file`	Yes
`size`	Yes
`tris`	Yes
`unit`	Yes
`parts`	No
`piece`	No
`format`	Yes
`images`	No
`meshes`	No
`checked`	No
`clashes`	No
`guessed`	No
`measures`	No
`warnings`	Yes
`materials`	Yes
`degenerate`	No
`references`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv3.0.0Sep 30, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description goes further, disclosing that units are guessed unless unit= is given, that warnings are emitted for missing textures/material libraries, and that check=clashes finds interpenetration but not touching — real behavioral context beyond the annotations.

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

Conciseness3/5

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

Content is largely front-loaded and every clause concerns calling the tool, but it is delivered as enormous run-on sentences that cram the return shape, parameters, and warnings together, hurting readability. Not padded, but poorly structured.

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?

Given six optional params and a rich annotation set, the description covers inputs, units, warnings, and clash-vs-touch semantics adequately. It also describes the return shape even though an output schema exists, which is redundant but not harmful.

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 description coverage is 100%, so the schema already documents all six parameters, including the check/tol semantics ('touching is not a clash'). The description mostly restates these; it adds only slight nuance (e.g. part keeps 'the parts named so'), so the baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb and resource ('Inspect an imported 3D model') and clarifies the two inputs — a placed piece (id) or a pre-placement file — which separates it from placement/editing siblings. It is dense but the core operation is unambiguous.

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

Usage Guidelines4/5

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

It states when to use it: 'before placing it' for a file, and for a piece that 'looks wrong after place model=…' instead of reading the file, with 'place model=… imports one' as the contrasting sibling. Explicit exclusions or a full alternatives list are absent, so it stops short of 5.

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