Skip to main content
Glama

Capture Electron Scenario

capture_electron_scenario
Destructive

Execute provider-owned Electron scenarios with caller-defined clicks, waits, reloads, crashes, and deep links when passive observation cannot exercise behavior; return process, session, IPC evidence.

Instructions

Use this for a provider-owned Electron run when passive CDP or Inspector observation cannot exercise application behavior. REA owns startup and teardown, accepts caller-defined click/wait actions plus window-targeted renderer reload/crash and synthetic open-url/second-instance delivery, and returns correlated window/WebContents/process/preload/session/navigation/shell/IPC evidence without retaining payload values. Actions wait for completion or request cancellation; a missing click target can keep the request pending. Results identify observed and unavailable event families, coverage status, action targets, and truncation. Cleanup failures retain collected observations with explicit cleanup uncertainty. External shell, navigation, permission, download, popup, updater, and OS-integration effects are blocked and recorded. Use passive Electron tools for observation-only work.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "args": [],
      "actions": [
        {
          "kind": "click",
          "step_id": "exercise-ipc",
          "selector": "#run"
        }
      ],
      "executable_path": "/Applications/Electron.app/Contents/MacOS/Electron",
      "application_path": "/Applications/Example.app/Contents/Resources/main.js"
    },
    "name": "capture_electron_scenario"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNo
actionsNo
executable_pathYesAbsolute local filesystem path for the Electron executable; relative paths are rejected.
application_pathYesAbsolute local filesystem path for the Electron application; relative paths are rejected.
application_rootNoAbsolute local filesystem root for application-relative paths; omit to derive it from the application path. Relative paths are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructive/openWorld/non-idempotent, and the description goes well beyond them: REA owns startup and teardown, payload values are not retained, actions block until completion or cancellation, cleanup failures preserve observations with explicit uncertainty, and external shell/navigation/permission/download/popup/updater effects are blocked and recorded. That is substantial disclosure of side effects and failure semantics for a destructive tool.

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?

Front-loaded with the use condition and the scope of ownership, and every sentence carries operational information rather than filler. It is one very dense paragraph, however, so individual guarantees (cancellation, cleanup uncertainty, blocked effects) are harder to scan than a short bulleted structure would allow.

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?

With no output schema, the description takes on the return-value burden and does so: it lists the evidence families returned, coverage status, action targets, truncation, and cleanup uncertainty. It still leaves out prerequisites such as required privileges or platform constraints for launching an Electron binary, which matters for a destructive open-world tool.

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 60%, and the description compensates by enumerating the action vocabulary (click, wait, renderer reload/crash, open-url/second-instance delivery) and noting window targeting, which maps to the window_index field the schema does not describe. It says nothing about args, executable_path, application_path, or application_root beyond what the schema's own path descriptions already state, so it is not fully compensating.

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?

States a specific verb-and-resource combination: launch a provider-owned Electron run, drive it with caller-defined actions, and return correlated runtime evidence. It also separates itself from observation-only siblings ('passive CDP or Inspector observation cannot exercise application behavior'), so the agent can tell it apart from inspect_electron_page without opening either schema. The core action verb is slightly buried inside a very dense sentence, which keeps it off a 5.

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?

Explicitly names the prerequisite condition for use (passive observation cannot exercise behavior) and the exclusion path ('Use passive Electron tools for observation-only work'). It also flags the operational caveat that a missing click target can leave the request pending, which is exactly the kind of selection-relevant risk an agent needs before invoking.

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