Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_set_view

Changes the drawing view or zooms to fit visible objects before taking screenshots. Use it to set top, orthogonal, or isometric views without modifying the document.

Instructions

Change the drawing view or zoom to fit, typically before vw_screenshot. Changes how the user sees the document, not the document itself, so it is not journaled and vw_revert_last does not undo it. For a view-independent picture use vw_render_layers instead. Returns {view, fit}.

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_set_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
fitNoTrue zooms so every object on visible layers fits the window.
viewNoView to switch to: 'top_plan' (2D plan), the orthogonal 3D views 'top', 'bottom', 'front', 'back', 'left', 'right', or the isometrics 'iso', 'iso_right', 'iso_left'. Omitted: the view is left as it is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / fit / description
      Added value: +"True zooms so every object on visible layers fits the window."
    • addedInput schema / properties / view / description
      Added value: +"View to switch to: 'top_plan' (2D plan), the orthogonal 3D views 'top', 'bottom', 'front', 'back', 'left', 'right', or the isometrics 'iso', 'iso_right', 'iso_left'. Omitted: the view is left as it is."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

The annotations only supply readOnlyHint=false, destructiveHint=false, openWorldHint=false, leaving the agent unsure why a non-destructive tool is flagged non-read-only. The description resolves that by explaining it changes only how the user sees the document, that the change is not journaled, and that `vw_revert_last` does not undo it — behavior no structured field carries. It also previews the return payload ("{view, fit}").

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?

Four short sentences, front-loaded with the action, then the sibling alternative, then the caveat, then the return shape. Every sentence supplies information the agent cannot get from the name, schema, or annotations.

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?

With only two optional parameters, full schema coverage, annotations present, and the return shape stated inline in lieu of an output schema, nothing an agent needs in order to call this correctly is missing.

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%: `fit` and `view` both have detailed descriptions including the full enum vocabulary of views. The prose adds only the summary phrase "Change the drawing view or zoom to fit," which maps one-to-one onto the two already-documented parameters, so baseline 3 is appropriate.

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 definition opens with a specific verb and resource ("Change the drawing view or zoom to fit") and immediately contrasts itself with the sibling `vw_render_layers` for a view-independent picture. An agent can distinguish this from `vw_screenshot`, `vw_render_layers`, and `vw_revert_last` without opening any schema.

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?

It gives positive timing guidance ("typically before vw_screenshot"), names the explicit alternative for the other use case ("For a view-independent picture use vw_render_layers instead"), and states an exclusion (this is not undone by vw_revert_last). When-to-use, when-not-to-use, and the alternative are all present.

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