Skip to main content
Glama
Sign In

Wandy3D

by com.wandy3d
OverviewDiscussionsAdmin

Make papercraft, laser layers, bricks or a flexi toy

make_craft

Turn one of the user's models into a craft to build by hand: papercraft (a PDF to print, cut and glue), laser (SVG layers for a laser cutter), bricks (building instructions and a parts list) or flexi (a print-in-place jointed toy; needs a rigged version from rig_model). Paid per new build — papercraft 10, laser 10, bricks 20, flexi 30 credits (a repeat or a failed build is not charged): tell the user the price and get their OK first. The files come as a ZIP. Takes 1–15 min; may return a task_id for get_task.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model_id": "<model_id>",
      "kind": "<kind>"
    },
    "name": "make_craft"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYespapercraft, laser (laser-cut layers), bricks or flexi (print-in-place toy)
optionsNoOptional settings of the chosen craft, e.g. {"size_cm": 25} — papercraft: detail simple|medium|detailed|expert, paper a4|letter, size_cm 8–45, color print|white; laser: height_cm 5–60, thickness 3|4|5|6, bed xtool_s1|glowforge|a4|a3|letter, kerf 0–0.4, holes none|3|5, guides true|false; bricks: size small|medium|large, palette full|basic, hollow true|false; flexi: length_cm 8–30, joints auto|few|many, clearance 0.25|0.35|0.45. Left out = the default.
model_idYesmodel_id of one of the user's models (list_models / get_task)
wait_secondsNoHow long to wait for the result before answering with a task_id (0–50 s, default 30)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only mark this as a non-idempotent mutation; the description goes well beyond by disclosing per-kind credit costs, the no-charge rule for repeats and failed builds, ZIP delivery, 1–15 min runtime, and possible task_id returns. It is not a contradiction of idempotentHint=false, since the free-repeat rule is about billing rather than repeat side effects. A 5 is withheld only because failure modes beyond 'failed build is free' are not described.

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

Conciseness5/5

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

Front-loaded with the action, then the four kinds, then cost, then output format and timing. Every clause carries operational information an agent needs before calling; nothing is redundant.

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 return packaging (ZIP), latency, async behavior (task_id → get_task), and the credit/consent workflow. For a 4-parameter, fully documented schema tool, nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so a baseline of 3 is the floor; the description still adds meaning by explaining what each kind produces and why a rigged model is required for flexi. The credits-per-kind mapping also makes 'kind' choice a cost decision, which the enum alone does not convey. Option-level settings are correctly left to the 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?

States a specific verb ('Turn one of the user's models into a craft') plus the four concrete output kinds and what each produces (PDF, SVG layers, instructions+parts list, print-in-place toy). That detail is enough to separate it from siblings like make_low_poly or export_model without opening the schema.

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 preconditions and routing: flexi 'needs a rigged version from rig_model', a model_id must come from list_models, and long runs should be polled via get_task. It also mandates price disclosure and user OK before charging. The only gap is no explicit statement of when NOT to use it instead of a sibling such as make_low_poly.

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

All Wandy3D 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