Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_apply_class_standard

Apply a consistent Spotlight class standard (colors and line weights) to a Vectorworks document; create missing classes and optionally restyle existing ones without changing objects.

Instructions

Give the document a consistent set of Spotlight classes with colours and line weights. Use it once per show file so plots look tidy and layers can be filtered; for a single ad-hoc class use vw_create_class. Missing classes are created and styled; existing ones are left alone unless overwrite=True. No object changes class: afterwards pass class_name= to the insert tools or use vw_set_record. One revertible step (created classes are deleted, restyled ones restored). Returns {standard, created: [...], restyled: [...], unchanged: [...], note?}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "vw_apply_class_standard"
  }
}

Input Schema

NameRequiredDescriptionDefault
onlyNoLimit the work to these class names or name prefixes, for example ['Lighting', 'Rigging-Truss']. Omitted: the whole standard.
documentNoName of the document this call may change, as listed by vw_list_documents. If given and another document is in front, nothing changes and the call fails; use vw_switch_document first. Always pass it for writes.
standardNoName of the bundled class standard. 'spotlight' (the only one today) defines Lighting-Instruments / -Labels / -Positions / -Focus Points / -Cables, Rigging-Truss / -Hoists, Stage-Decks / -Steps, Soft Goods, Audio, Video, Scenery, People, Venue-Architecture / -Seating, Notes, Dimensions.spotlight
overwriteNoTrue restyles classes that already exist (pen, fill, line weight; recorded for revert). Default False leaves existing classes alone.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.1
    • addedInput schema / properties / document / description
      Added value: +"Name of the document this call may change, as listed by vw_list_documents. If given and another document is in front, nothing changes and the call fails; use vw_switch_document first. Always pass it for writes."
    • addedInput schema / properties / only / description
      Added value: +"Limit the work to these class names or name prefixes, for example ['Lighting', 'Rigging-Truss']. Omitted: the whole standard."
    • addedInput schema / properties / overwrite / description
      Added value: +"True restyles classes that already exist (pen, fill, line weight; recorded for revert). Default False leaves existing classes alone."
    • addedInput schema / properties / standard / description
      Added value: +"Name of the bundled class standard. 'spotlight' (the only one today) defines Lighting-Instruments / -Labels / -Positions / -Focus Points / -Cables, Rigging-Truss / -Hoists, Stage-Decks / -Steps, Soft Goods, Audio, Video, Scenery, People, Venue-Architecture / -Seating, Notes, Dimensions."
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare that this is a non-read-only, non-destructive, closed-world call. The description goes well beyond: missing classes are created, existing ones are untouched unless overwrite=True, no object is re-classed (so the caller must follow up with class_name= or vw_set_record), and the whole thing is a single revertible step with defined rollback. That is exactly the mutation and recovery context an agent needs.

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?

Five tight sentences: purpose first, then alternative, then mutation semantics, then the follow-up requirement, then the return shape. Every sentence carries information an agent would otherwise have to discover by trial.

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

Completeness4/5

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

No output schema exists, but the description summarises the return object (standard, created, restyled, unchanged, note?) so the agent knows what to inspect. Combined with the explicit rollback semantics and the document/overwrite behaviour, it is nearly complete for a four-parameter mutation tool; only re-run idempotency is left implicit.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents only, document, standard and overwrite. The description restates the overwrite semantics and names the standard's contents, but adds no format or edge-case detail for the `only` prefix matching beyond what the schema says. Baseline 3 applies.

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 concrete verb and resource — applying a bundled Spotlight class standard with colours and line weights — and immediately contrasts it with vw_create_class for the single-class case. The agent can distinguish the bulk-standard operation from the ad-hoc create without reading either 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 explicit usage context ('once per show file so plots look tidy and layers can be filtered') and names the alternative (vw_create_class) with the condition that selects it. What's missing is a when-not case for re-running on an already-standardised file, though the unchanged list and overwrite flag imply it.

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