Skip to main content
Glama

OwlCAD

by com.owlcad.mcp
OverviewDiscussionsAdmin

Export STEP (a job)

export_step

Export a SAVED project as STEP (beta) — real B-rep, not a mesh, for CAD interchange. OCCT takes minutes, so this runs as a JOB: call with projectId to get a jobId, then call again with that jobId alone until status is "done", waiting retryAfterMs between polls (polling faster burns your call budget). A poll reports waitingMs; a job still "queued" after a few minutes is stuck, so stop polling and start a new one. Needs a saved project — run save_project first; it cannot export an inline tree. Pro accounts only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fitNoBeta: fit analytic curved surfaces (cylinders, cones, spheres, tori) instead of flat facets. Default false.
jobIdNoA handle from an earlier call. Send it ALONE to poll.
projectIdNoThe saved project to export. Omit when polling.
keepFacetsNoKeep a SET facet count as flat faces: a cylinder, cone, tube or sphere whose side count was set (a hexagonal nut trap, a .scad sphere($fn=8)) exports with the flat faces its STL has, while an automatic count stays a true curved surface. Default true, as in the editor; false exports every round shape curved.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / fit / description
      Previous value: -"Fit analytic surfaces (cylinders, planes) instead of emitting a faceted solid. Default false."New value: +"Beta: fit analytic curved surfaces (cylinders, cones, spheres, tori) instead of flat facets. Default false."
  2. Changed1 schema field changed
    • addedInput schema / properties / keepFacets
      Added value: +{
+  "description": "Keep a SET facet count as flat faces: a cylinder, cone, tube or sphere whose side count was set (a hexagonal nut trap, a .scad sphere($fn=8)) exports with the flat faces its STL has, while an automatic count stays a true curved surface. Default true, as in the editor; false exports every round shape curved.",
+  "type": "boolean"
+}
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations (which only mark it non-read-only, non-idempotent, non-destructive) by disclosing the multi-minute OCCT runtime, the job/polling model, the retryAfterMs backoff requirement and the call-budget cost of over-polling, the waitingMs poll field, and the stuck-job failure mode. It does not describe the success artifact (file handle/download) beyond the done status, keeping it at 4 rather than 5.

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?

Dense and front-loaded with the core action and output format first, then the job mechanics. Every sentence carries information, though the parenthetical asides (call budget, stuck jobs) make it longer than strictly needed.

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?

No output schema exists, yet the description covers the returned fields (jobId, status, waitingMs), the terminal condition (status 'done'), and the failure condition (stuck 'queued'). Combined with the auth/plan constraint and prerequisite, an agent has everything needed to call it correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: projectId is for starting a job and yields a jobId, jobId must be sent alone to poll, and retryAfterMs governs poll spacing. That call-pattern semantics is genuinely additive over the per-parameter schema text.

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 (Export), resource (a SAVED project), and output format (STEP, real B-rep not a mesh), plus the interchange use case. Clearly distinguishable from the sibling export/export_2d tools by naming STEP and the CAD-interchange intent.

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

Usage Guidelines5/5

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

Explicitly states when to use it (saved project only, pro accounts only), the prerequisite alternative (run save_project first; cannot export an inline tree), and the exact two-phase calling procedure with projectId then jobId. It also tells the agent when to stop (a job stuck 'queued' after a few minutes) and to start a new one.

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

All OwlCAD toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources