Skip to main content
Glama

Inspect Web Page

inspect_web_page
Idempotent

Passively capture a page's DOM, accessibility, scripts, network and console metadata, workers, and storage inventory through CDP as evidence, without evaluating JavaScript, navigating, clicking, or mutating the page.

Instructions

Passively inspect one selected page target through CDP without evaluating JavaScript, navigating, clicking, closing, or mutating the page. If no origin filter is supplied, capture is scoped to the target's current origin. Returns DOM structure, accessibility, scripts, resources, attach-window network and console metadata, workers, and redacted storage inventory as Evidence.

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_BROWSER_TARGETS",
      "cdp_endpoint": "http://127.0.0.1:9222"
    },
    "name": "inspect_web_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
allowed_originsNo
include_console_textNoWhether to include console text in the result.
include_storage_keysNoWhether to include storage keys in the result.
include_script_sourcesNoWhether to include script sources in the result.
include_json_body_shapesNoWhether to include json body shapes in the result.
include_websocket_shapesNoWhether to include websocket shapes in the result.
include_accessibility_textNoWhether to include accessibility text in the result.
include_storage_fingerprintsNoWhether to include storage fingerprints in the result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare openWorldHint, idempotentHint, and destructiveHint=false, but the description adds real value by enumerating what the tool will not do to the page and by stating the default capture scope ('if no origin filter is supplied, capture is scoped to the target's current origin'). It also previews the evidence categories returned, which substitutes partly for the absent output schema. Minor tension worth noting: annotations set readOnlyHint=false while the description stresses non-mutation — plausibly because a CDP attach alters session state, so this is a nuance rather than a contradiction.

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?

Two sentences, no filler, with the core action and its constraints front-loaded before the scoping rule and return inventory. The final enumeration of evidence types is long but informative rather than redundant, since no output schema exists to carry it.

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?

With 11 parameters, no output schema, and mutation-adjacent CDP behavior, the description covers purpose, non-effects, scoping default, and return categories well. It leaves unexplained the observation window (observation_ms default 500ms) and the semantics of the include_* toggles, which materially change what evidence is collected — an agent cannot tell from the description how to shape the capture.

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 82%, so the schema already documents most fields and the baseline of 3 applies. The one genuine addition is the documented default behavior of allowed_origins; the eight include_* toggles, observation_ms (whose 500ms default governs how long capture runs), and the required cdp_endpoint/target_id pairing get no explanation beyond their schema text.

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?

The description gives a specific verb and resource ('passively inspect one selected page target through CDP') and immediately bounds it with a negative list (no JS evaluation, navigation, clicking, closing, mutation), which separates it from execution-oriented siblings like observe_web_execution. It stops short of naming any sibling explicitly, so the differentiation is behavioral rather than direct.

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?

Usage is implied by the passivity constraint: this is the tool for reading a page's state without driving it, and the origin-scoping default is stated. There is no explicit 'use this instead of X when Y', no prerequisite statement (e.g. that a target must first be obtained from a target listing, which is only visible in the schema example), and no guidance on when a sibling capture tool would be preferable.

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