Skip to main content
Glama
Electron Debug MCP Server

Electron Debug MCP Server

by amafjarkasi

save_screenshot

Idempotent

Capture a screenshot and save it to a local PNG/JPEG file; optionally clip the image to a specific CSS selector element.

Instructions

Capture a screenshot and write it to a local file path (PNG/JPEG); optional selector clips to element

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": "save_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute or relative file path to write
formatNo
qualityNo
selectorNoOptional CSS selector — capture only that element's bounding box
targetIdNo
processIdNoTarget process ID. Omit if only one app is running.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.15.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and idempotentHint=true, and the description is consistent with that (it writes a file). Beyond annotations it adds the format options and the selector-clipping behavior, but it is silent on operationally significant details: whether an existing file at the path is overwritten or errors, whether parent directories are created, and what permissions or browser state are required.

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?

A single dense front-loaded sentence with no filler; the purpose and the two optional behaviors arrive in order of importance. The parenthetical and semicolon keep it compact without muddling meaning.

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?

The formatting and clipping behavior are stated, but the write-destination semantics that matter most for a 2-write-flag tool, silent overwrite of an existing path and whether the resulting path is reported, remain unstated.

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 50%, so baseline is 3. The description maps to format (PNG/JPEG) and selector (clips to element), but adds nothing for quality (scope? jpeg-only?) or targetId, which are undocumented in both schema and description.

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?

Names a specific verb+resource pair (capture a screenshot) plus the concrete effect (write to a local file path), which is more than a restatement of the name. It does not explicitly distinguish itself from the sibling screenshot tool, so the agent must infer that this variant is the one that persists to disk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States what happens (file written, PNG/JPEG, optional clipping) but gives no when-to-use or when-not guidance. It never tells the agent to prefer this over the sibling 'screenshot' tool when a saved artifact is needed, or which situations call for a file versus an in-memory capture.

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