Skip to main content
Glama
pzfreo

build123d-mcp

workflow_hints

Get guidance on using available tools effectively. Use at session start or when unsure which tool to reach for.

Instructions

Return guidance on how to use these tools effectively. Call this at the start of a session or whenever unsure which tool to reach for.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The tool handler function for 'workflow_hints'. Decorated with @mcp.tool(), it returns a static string containing an 8-point workflow guide for using the MCP tools effectively.
    @mcp.tool()
    def workflow_hints() -> str:
        """Return guidance on how to use these tools effectively. Call this at the start of a session or whenever unsure which tool to reach for."""
        return """\
    BUILD123D-MCP WORKFLOW GUIDE
    
    1. ORIENT FIRST
       At the start of a session, call session_state() to see what geometry, objects, and
       snapshots are already active. Call health_check() if you suspect a missing dependency
       (VTK, display, STEP export). Call version() to confirm the server version.
    
    2. MEASURE BEFORE YOU LOOK
       After building or modifying geometry, verify with measure() before calling render_view.
       Numbers are unambiguous; renders can look correct even when the geometry is wrong.
       Recommended order: execute → measure → render_view (if you need to see it).
    
    3. VERIFY BOOLEAN OPERATIONS WITH TOPOLOGY
       After any cut, union, or intersection, call measure(topology) on the result.
       A successful boolean changes face/edge/vertex counts; a failed one leaves them unchanged.
       measure(volume) confirms the magnitude of the change.
    
    4. MEASURE THE OBJECT IN QUESTION — NOT A PROXY
       When debugging, call measure() on the actual disputed object.
       Testing an isolated reconstruction and using that as proof of the full assembly is a
       common mistake — the two may differ in ways that matter.
    
    5. NAME AND AUDIT YOUR SHAPES
       Use show(shape, "name") after creating important geometry — it also sets current_shape.
       The execute() output immediately confirms name, volume, and face count.
       Call session_state() for a full JSON view of all active shapes, objects, and snapshots.
    
    6. CHECKPOINT BEFORE EXPERIMENTS
       Call save_snapshot("name") before any operation you might want to undo.
       Snapshots are instant. restore_snapshot("name") reverts geometry without re-running code.
       Use diff_snapshot("name") to see what changed; pass format="json" for structured output.
    
    7. CROSS-SECTIONS FOR INTERNAL GEOMETRY
       render_view with clip_plane + clip_at reveals interior features.
       Use clip_at to position the cut at a specific world coordinate, not just the midpoint.
       Combine with measure(topology) on the unclipped shape to confirm what you see.
    
    8. PART LIBRARY
       search_library("keyword") returns full parameter specs.
       Call load_part("name", '{"param": value}') immediately — no second lookup needed.
       Unspecified parameters use the defaults shown in search results.
    """
  • Registration of the 'workflow_hints' tool via the @mcp.tool() decorator on line 168.
    @mcp.tool()
    def workflow_hints() -> str:
        """Return guidance on how to use these tools effectively. Call this at the start of a session or whenever unsure which tool to reach for."""
  • The tool has no parameters (empty signature) and returns a string. The docstring on line 170 serves as the description.
    @mcp.tool()
    def workflow_hints() -> str:
        """Return guidance on how to use these tools effectively. Call this at the start of a session or whenever unsure which tool to reach for."""
  • Test assertion confirming 'workflow_hints' is registered as a tool name.
    "search_library", "load_part", "workflow_hints", "session_state", "health_check",
Behavior3/5

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

No annotations provided, so description carries full burden. It describes the tool as returning guidance, implying a read-only, non-destructive action. However, it doesn't disclose output format or side effects, which is acceptable for a simple guidance tool but could be improved.

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?

Two sentences, front-loaded with purpose, no unnecessary words. Every sentence earns its place.

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?

For a tool with no parameters and a clear purpose, the description provides enough context for an agent to know when to call it. Output schema exists but is not needed in description because return values are self-evident.

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?

Input schema has zero parameters, so baseline is 4. The description adds meaning beyond the schema by explaining what the tool returns (guidance), which is sufficient.

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 returns 'guidance on how to use these tools effectively', which is a specific verb+resource combination. It distinguishes itself from sibling tools (which perform concrete actions) by providing meta-guidance.

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?

Explicitly says to call 'at the start of a session or whenever unsure which tool to reach for', giving clear context. It doesn't explicitly mention when not to use, but the positive guidance is sufficient.

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