Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

capture_view

Capture a PNG of the active SOLIDWORKS document's graphics view to inspect the model visually, with optional section cut, region, zoom, custom camera direction, and file output.

Instructions

Capture a PNG of the active document's graphics view, to inspect the model visually: a standard view, or a camera direction with an up direction (the default up is +Y; for a Z-up model give up = {x:0, y:0, z:1}). A picture wider or taller than 1280 pixels is written to output_path only, not sent back. A section cut by a plane can be added for the capture only. To see detail, return only part of the picture: region (fractions from the top left) or zoom (1-20, on the centre). The screen is left as it was: the on-screen view is restored afterwards, whatever view or zoom_to_fit was used.

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": "capture_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
upNoWith direction: the model direction that points up in the picture (default +Y)
unitNoUnit of the section offset (mm, cm, m, inch or ft)
viewNoView orientation ('current' keeps what is on screen)current
zoomNoInstead of region: enlarge the centre of the picture by this factor (1-20)
widthNoExact picture width in pixels (64-4096)
heightNoExact picture height in pixels (64-4096)
regionNoOnly this part of the picture, in fractions (0-1) from the top left, at full resolution
sectionNoCut the model with a plane for this capture only
max_sizeNoLongest side in pixels (256-1280), when width / height are not given
directionNoInstead of view: where the camera is, seen from the model, in model axes. {0,0,1} = front view, {1,1,1} = an isometric view.
output_pathNoAlso write the PNG to this file on the computer, e.g. C:\Work\door.png
zoom_to_fitNoZoom to fit before capturing
return_imageNofalse = do not send the picture back, only write the file
hide_annotationsNoHide dimensions, notes, planes, axes, origins and sketches for the capture
white_backgroundNoPlain white background for the capture

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the non-obvious rule that images larger than 1280 px are written to output_path only and not returned, that a section cut applies to this capture only, and that the on-screen view is restored afterwards. Gaps remain around file writing (overwrite behaviour, permissions, and what happens when an oversized image is requested without output_path).

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?

Purpose is front-loaded in the first clause, and each subsequent sentence carries a distinct, non-redundant fact (up-vector semantics, size/return rule, section scope, region versus zoom, view restoration). There is no filler or repetition of schema defaults for their own sake.

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?

For a 15-parameter capture tool with no annotations and no output schema, the description covers the behaviours that matter most: view selection, sizing/return interaction, muting of section cuts, and screen restoration. It does not describe the shape of the returned image payload or the interaction of return_image=false with output_path, which an agent must infer.

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 the baseline is 3, but the description adds real meaning beyond the schema: the default up is +Y with a Z-up example, up pairs with direction while view is the alternative, region is measured from the top left, and zoom enlarges the centre. These clarifications genuinely reduce misuse of the 15 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Capture a PNG of the active document's graphics view, to inspect the model visually" gives a specific verb (capture) and resource (graphics view PNG), and the goals differ plainly from view-creation siblings such as add_section_view or add_detail_view. It stops short of naming any sibling to route against, so it is clear but not fully differentiated.

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?

It states the two main invocation modes (a standard view, or a direction with an up vector) and the condition for each, plus the "to see detail, return only part of the picture" guidance choosing between region and zoom. What is missing is any explicit exclusion or pointer to an alternative tool, e.g. when to use this versus add_section_view for a cut view.

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

Deploy Server

Other Tools