Skip to main content
Glama
fusion-cam

fusion-cam

screenshot

Capture the active viewport as a PNG and return its file path, optionally reorienting to iso, top, front, or right views.

Instructions

Save the active viewport as a PNG and return its path (sizes in px).

view: iso | top | front | right | current ('current' keeps the user's camera; the others reorient and fit the view). Default path: /test_output/screenshot__.png. Read the PNG to look at it. A timed-out call may still finish: call status before retrying.

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": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
viewNoiso
widthNo
heightNo
timeout_sNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.6/5.0
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 substantial work: it discloses that the tool writes a file to disk, gives the default path template with repo root and timestamp, explains that non-'current' views reorient and fit the camera, and warns that a timed-out call may still complete. It omits whether an existing file at a supplied path is overwritten, which is the main remaining gap for a write-side-effect tool.

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?

The output path is stated first, then parameters, then post-call guidance, so the most important information is front-loaded. Each clause adds new information, including the non-obvious retry warning, and there is no repetition of the tool name or filler.

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 five-parameter tool with an output schema and zero schema descriptions, this is complete: it covers all parameters in prose, the side effect of writing a file, camera semantics, and failure/retry behavior. Return value detail is rightly deferred to the output schema.

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

Parameters5/5

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

Schema description coverage is 0% and no parameter has a schema enum, yet the description compensates fully: it enumerates the accepted view values and their camera behavior, documents the default path pattern, states that width/height are in pixels, and explains timeout_s behavior plus retry semantics. Every parameter gains meaning the bare schema does not provide.

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 first sentence names a specific verb and resource: it saves the active viewport as a PNG and returns the path. It also states the unit (px) and the artifact produced, so the agent can tell this apart from inspection or status siblings without opening the 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?

It gives clear operational guidance: pick a named view or 'current' to preserve the user's camera, read the returned PNG to actually look at it, and call status before retrying after a timeout. It stops short of naming an alternative sibling or stating when not to take a screenshot, so the routing guidance is contextual rather than exhaustive.

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