Skip to main content
Glama
pzfreo

build123d-mcp

verify_spec

Checks a built 3D solid against a design-intent spec to verify requested features and constraints match the actual geometry, returning a conformance report with PASS/FAIL/UNVERIFIED status.

Instructions

Verify the built solid against a declared design-intent spec — did you build what was requested? Checks requested features/constraints against the actual geometry and returns an evidence-tiered conformance report; unlike validate() (is the solid valid?) this answers requested-vs-built. Provide the spec as inline JSON (spec=) or a .json file path (spec_path=). Supported spec keys: envelope_mm {x/y/z:[lo,hi]} (bbox size in range), solid {count, valid}, volume_mm3 {min,max}, features:[{kind:"hole_pattern",pattern:"bolt_circle"|"linear_array",holes,bcd_mm|pitch_mm,diameter_mm} | {kind:"hole",count,diameter_mm,depth_mm,through:bool,counterbore:{diameter_mm,depth_mm}|true|false,spotface:{...}} | {kind:"boss",diameter_mm,height_mm} | {kind:"countersink",count,major_diameter_mm,drill_diameter_mm,included_angle_deg,depth_mm} | {kind:"material_at_point",point:[x,y,z],expect:"solid"|"void"} | {kind:"wall_thickness_at",point:[x,y,z],direction:[dx,dy,dz],expect_mm:[lo,hi]}] (counterbore/spotface: true=present, false=absent; a depth_mm matches the recognizer-measured depth which may differ from a drawing callout; material_at_point asks is-this-point-inside-the-solid to disambiguate add-vs-remove features the recognizers can't see; wall_thickness_at measures the local wall thickness along a line through the point and range-checks it — the thin-wall blind spot; both are measured-tier but frame-DEPENDENT: absolute coordinates tied to the part's own frame, verifying a same-session build, not portable across a repositioned part; a point in no wall reads UNVERIFIED), parameters:[{name,min,max}] (top-level numeric assignment in range), min_wall_mm (global minimum wall ≥ value, measured tier via augura), targets:[{name,verifiable:false}] (→UNVERIFIED). Returns JSON: {conformance:[{requirement, status:PASS|FAIL|UNVERIFIED, tier:measured|structural|recognised|unverified, actual/found/hint}], summary:{pass,fail,unverified,conforms}, note}. conforms = no FAILs; UNVERIFIED requirements are NOT met (out of scope), never counted as passing. Dimensions match within max(0.1mm, 1%); counts exact; an unrecognised feature kind is UNVERIFIED, not a false FAIL. Not a certification. Re-run after edits as a regression/acceptance gate. object_name: named object from show() (default: current shape).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
specNo
spec_pathNo
object_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

With no annotations, the description carries full burden. It discloses the evidence-tiered conformance report, tolerance behaviors, handling of unrecognised features, frame-dependency of point checks, and that it is not a certification. It does not explicitly state if the tool is read-only, but the context implies it does not modify state.

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?

The description is information-dense but presented as a single wall of text without structure like bullet points or sections. It is front-loaded with purpose but could be better organized for readability, especially given the extensive list of spec keys.

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

Completeness5/5

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

Given the presence of an output schema, the description adequately covers the return format and meaning. It thoroughly explains input spec keys, edge cases (frame-dependency, UNVERIFIED status), and usage notes like default object_name. The description is complete for a verification tool of this complexity.

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

Parameters5/5

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

Despite 0% schema description coverage, the description provides comprehensive semantics for all three parameters. It explains how to provide the spec as inline JSON or file path, details all supported spec keys with examples, and clarifies the object_name parameter. This fully compensates for the schema's lack of descriptions.

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?

The description clearly states the tool's purpose with a specific verb-resource combination: 'Verify the built solid against a declared design-intent spec.' It distinguishes itself from sibling tool validate() by answering 'requested-vs-built' versus 'is the solid valid?'.

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?

The description provides clear context for when to use this tool, contrasting with validate() and recommending re-run after edits as a regression/acceptance gate. It explains the output's conforms meaning but does not explicitly list when not to use it among other siblings like design_audit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pzfreo/build123d-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server