Skip to main content
Glama

create_extrusion

Extrude a 2D outline into a solid with clean quad sides, including holes, rolled rims, and crowns for panels, brackets, plates, logos, or gears.

Instructions

Extrude a 2D outline into a solid with clean quad sides - for anything defined by a silhouette: chair/shelf side panels, brackets, plates with holes, table aprons, logos, gears, cookie-cutter shapes. Draw in the plane you think in (front elevation = XZ). Holes, rolled rims and crowns are built as a well-formed surface (even triangles, real quarter-round rims): give the shape here instead of adding a big Bevel or pushing vertices afterwards. Holes must lie inside the outline (checked).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
backNoparallel = back follows the crown (constant-thickness pressed shell).flat
nameNoExtrusion
bevelNoRounded edges via an angle-limited Bevel modifier with hardened normals: width in metres (e.g. 0.002 for a 10 cm part), or {width, segments, angle}. true = automatic width.
crownNoPressed/domed face: how far the front face rises above its rim (m), smooth from the edge inwards - side covers, tank badges, fenders, lids. Built into the surface (no folds), not a later bulge.
depthNoThickness, extruded symmetrically about the drawing plane.
holesNoInner outlines to cut through, same format.
planeNoXY: outline seen from the top (u=x, v=y), thickness along Z. XZ: outline seen from the front (u=x, v=z), thickness along Y. YZ: outline seen from the side (u=y, v=z), thickness along X.XY
originNoWhere the origin sits on the part's bounding box: center, bottom, top, left, right, front, back, min, max, or keep (geometry coordinates exactly as given). origin='bottom' + location z=0 stands a part on the floor.keep
parentNo
pointsYes2D outline [[u, v], ...] in metres (any winding). A third value sets that corner's fillet radius: [u, v, r].
shadingNoauto = smooth with sharp edges kept above smooth_angle (best default); smooth; flat.auto
spacingNoSurface point spacing for holed/rolled/crowned panels (m).
locationNoWorld position [x,y,z] (metres) of the object origin.
materialNoMaterial preset name (list_material_presets), or {preset, color, roughness, weathering, ...} like apply_material, or the name of an existing material. Presets with a real-world scan use Poly Haven automatically; {'polyhaven': 'mossy rock'} picks any Poly Haven texture by description.
rotationNoRotation [x,y,z] in degrees.
collectionNo
edge_radiusNoRound the front/back rims (rolled pressed-panel edge) - radius in metres.
hole_radiusNoRounded lip on every hole (m); default from edge_radius and the hole size.
subdivisionNoSubdivision Surface levels (1-3) for soft/organic shapes.
corner_radiusNoFillet radius for every corner (metres).
crown_falloffNoDistance from the edge where the crown reaches full height (default 35 % of the smaller extent).
edge_segmentsNo
interpolationNosmooth = treat points as a spline (organic outlines).linear
corner_segmentsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses useful behavioral traits about output quality and validation: 'clean quad sides', 'well-formed surface (even triangles, real quarter-round rims)', and that holes are checked. However, it omits other important behavioral context such as whether it creates a new object, modifies the scene, or has permission requirements.

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?

The description is front-loaded with the core purpose and then branches into examples, plane advice, and shape-handling notes. It is reasonably efficient, though the list of example parts and the mid-sentence parenthetical are slightly dense; every sentence still earns its place.

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 24 parameters, no output schema, and no annotations, the description covers the essential concept, key behaviors, and the main constraint (holes inside outline). It does not explain the full set of advanced options or the tool's return value, but the schema handles most parameter details and the core usage is clear.

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 79%, so the schema already documents most parameters. The description adds only minor semantic value beyond the schema, such as reinforcing that 'front elevation = XZ' (already in the schema) and noting that holes are validated, but it does not clarify the many other parameters (bevel, crown, subdivision, etc.).

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 ('Extrude a 2D outline into a solid') and immediately differentiates from other modeling approaches by scoping it to silhouette-defined parts with concrete examples. The phrase 'give the shape here instead of adding a big Bevel or pushing vertices afterwards' further distinguishes it from alternative workflows.

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?

Gives clear usage context ('for anything defined by a silhouette') and a list of example parts, and advises against a common alternative (post-hoc Bevel). However, it does not explicitly name when to choose this over sibling tools like create_sweep or create_loft, nor does it state exclusions.

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