Skip to main content
Glama

record_drawing_spec

Records a structured part specification from a drawing source to enable deterministic feature plan compilation and execution. Accepts archetype, dimensions, features, and internal features.

Instructions

Record a structured DrawingSpec (LEGACY/dormant spine — see docs/AUTOMATION_LANE.md).

Advisory only: does NOT mutate SolidWorks. Pins a structured part spec (the LLM's own reading, from any source) so compile_feature_plan_from_drawing_specrun_feature_plan can build it deterministically. Generating a part from a drawing is a legacy path, not the product focus (automation + reuse).

Args: source: Dict with pdf_path, page_number, crop_pdf_pts, render_path, note. interpretation: One-sentence part interpretation. archetype: One of axisymmetric_revolved, extruded_closed_profile, plate_hole_pattern, custom. dimensions: List of {name, value, units, status, source, tolerance, confidence, note}. status is grounded/derived/assumed/missing. features: List of {kind, label, tool, params, source_dimensions, confidence, note}. If tool is set, compile_feature_plan will use it directly; otherwise it emits archetype defaults. internal_features: List of {type, diameter_mm, radius_mm, depth_mm, axis, position_mm, status, note} — the dashed-line bores/grooves/threads to model. type is through_hole/blind_hole/counterbore/countersink/ groove/thread/radius_cut. radius_cut (a swept-arc / scooped cut) uses radius_mm instead of diameter_mm. verify_build_report reconciles each against the built tree to catch silently-dropped or wrong-sized features. views: Optional list of source-view notes/crops. assumptions: Assumptions explicitly chosen by the LLM/user. missing_dimensions: Required dimensions not visible in the source. confidence: Global confidence 0..10. notes: Free-form audit notes.

Returns the stored spec, warnings, expected_size_mm when inferable, and a short build recommendation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesNo
viewsNo
sourceYes
featuresNo
archetypeYes
confidenceNo
dimensionsNo
assumptionsNo
interpretationYes
internal_featuresNo
missing_dimensionsNo
Behavior5/5

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

No annotations are provided, so description carries full burden. It explicitly states 'Advisory only: does NOT mutate SolidWorks', clearly disclosing the non-mutating behavior. It also describes return values and the role in the pipeline, offering full transparency.

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?

Description is fairly long but well-structured, starting with purpose and key note, then listing args, then returns. It is front-loaded with the most important information. A bit verbose but justified by the number of parameters.

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?

Despite no output schema, description covers purpose, behavior, usage, all parameters, and return values. It references a document for more info. For a complex tool with 11 parameters, this is complete and provides all necessary context for an AI agent.

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?

With 0% schema coverage, description compensates fully by providing detailed parameter descriptions, including structure, allowed values, and notes. Each parameter is explained with examples and constraints (e.g., archetype options, internal_features types). This adds significant value beyond the bare schema.

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?

Description clearly states the tool records a structured drawing spec and distinguishes it from sibling tools by noting it is advisory-only, non-mutating, and part of a pipeline (compile_feature_plan_from_drawing_spec -> run_feature_plan). It also mentions the legacy path, providing specificity.

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?

Description explains when to use the tool (to record a parsed spec for deterministic build) and what it does not do (does not mutate SolidWorks). It references a pipeline flow but does not explicitly list alternatives or when not to use it. Still, the context and explicit mention of legacy path provide good guidance.

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/danielproxd2/MCP_CAD'

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