Skip to main content
Glama

vi_snapshot

Render a LabVIEW VI to PNG images of its block diagram, front panel, or connector pane, optionally including every hidden frame and downscaling large images.

Instructions

Render a VI to PNG images: block diagram, front panel and/or connector pane.

all_frames=true also renders every hidden case / sequence / event frame (one image per frame, in LabVIEW's order) — big VIs can produce dozens, so raise max_images deliberately. Images larger than max_px on their longest side are downscaled.

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": {
      "path": "<path>"
    },
    "name": "vi_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
panelNo
max_pxNo
diagramNo
connectorNo
all_framesNo
max_imagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.40.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose meaningful behavior: per-frame expansion ordering ('LabVIEW's order'), the volume cost of all_frames, and downscaling when the longest side exceeds max_px. The major remaining gap is that it never says how images are delivered (written to disk, returned as paths, embedded), which matters for a rendering tool with no output schema.

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

Conciseness4/5

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

Three sentences, front-loaded with the core purpose, then the expensive-option caveat, then the resizing rule — no filler. Minor friction from the slightly awkward 'raise max_images deliberately' phrasing, but nothing is wasted.

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

Completeness3/5

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

For a 7-parameter tool with no annotations and no output schema, the description covers render targets and cost behavior but omits where the resulting PNGs come back to the caller. That omission is the one thing an agent needs before invoking it and cannot recover from the schema.

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 0%, so the description must compensate and largely does: it names the three render-selector flags, ties all_frames to frame expansion, and explains that max_px is a longest-side downscale threshold rather than an absolute dimension. It does not explain max_images' exact semantics beyond 'how many images', and the required path parameter is left implicit as the VI to render.

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 and resource ('Render a VI to PNG images') plus the three renderable targets (block diagram, front panel, connector pane). That verb-plus-output-format framing cleanly separates it from text-oriented siblings like vi_dump, vi_info and vi_text.

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 real operational guidance: all_frames expands rendering to every hidden case/sequence/event frame, and the agent is told to raise max_images deliberately because large VIs can produce dozens of images. It does not explicitly name an alternative tool for non-visual inspection, so it stops short of full when/when-not routing.

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