Skip to main content
Glama

Inspect Electron Page

inspect_electron_page
Idempotent

Passively inspect an Electron file page via a loopback CDP endpoint and target ID to retrieve frames, DOM structure, resource paths, and scripts without executing renderer JavaScript or Electron APIs.

Instructions

Passively inspect one Electron file page by supplying its loopback CDP endpoint and target ID. The provider rechecks that the target currently exists at that endpoint and is a local file page. Returns frames, DOM structure, resource paths, and scripts without evaluating renderer JavaScript or invoking Electron APIs. The selected endpoint exposes every local file page and its metadata to this tool.

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": {
      "target_id": "TARGET_ID_FROM_LIST_ELECTRON_TARGETS",
      "cdp_endpoint": "http://127.0.0.1:9223"
    },
    "name": "inspect_electron_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
target_idYesExact CDP target identifier selected from the endpoint's target listing.
cdp_endpointYesLiteral loopback Chrome DevTools Protocol endpoint.
observation_msNo
include_script_sourcesNoWhether to include script sources in the result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Adds real context beyond the annotations: the provider re-verifies the target exists and is a local file page, and the inspection is passive ('without evaluating renderer JavaScript or invoking Electron APIs'), plus the privacy note that the endpoint exposes every local file page. There is an unresolved tension with readOnlyHint=false, which suggests the operation is not purely read-only, and the description neither explains nor reconciles that; it also says nothing about failure behavior when the target vanishes.

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?

Four sentences, front-loaded with the action and inputs, then validation, then what is returned and not performed, then the exposure caveat. Each sentence carries distinct information; only the returns list is slightly compressed rather than fully itemized.

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 and openWorldHint=true, the description does the work of stating the return surface (frames, DOM structure, resource paths, scripts) and the preconditions (target must currently exist and be a local file page). The main remaining gap is the effect of observation_ms on what gets captured, which an agent must infer.

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 coverage is 75%, so the schema largely documents the inputs. The description reinforces the semantics of cdp_endpoint (must be literal loopback) and target_id (must be the exact id already present at that endpoint), but says nothing about observation_ms or why include_script_sources is constrained to a fixed value, leaving those to the schema.

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?

Clear specific verb+resource: 'Passively inspect one Electron file page' with the inputs named (loopback CDP endpoint + target ID). The scope is narrow and concrete, and 'Electron file page' implicitly separates it from inspect_web_page, but no sibling is named explicitly so the differentiation is inferential rather than stated.

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

Usage Guidelines3/5

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

The description tells you what to supply (endpoint plus a target id that must already exist at that endpoint), which implies target ids come from a target-listing tool via the schema example. It gives no explicit when-to-use vs when-not guidance and no exclusions relative to inspect_web_page or capture_electron_scenario.

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