Skip to main content
Glama

Observe Web Session

observe_web_session
Idempotent

Arms a timed CDP observation window to capture a user's page session, recording navigation, redirect, lifecycle, and failure events while optionally limiting retention to allowed origins.

Instructions

Arm a CDP observation window of the requested duration while the user operates the page. By default it follows the selected target's current origin; an explicit origin list controls which origins may be retained. Records navigation, redirect, lifecycle, and failure events.

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",
      "observation_ms": 10000
    },
    "name": "observe_web_session"
  }
}

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true, destructiveHint=false and idempotentHint=true; the description adds that the tool is an arming operation with a bounded time window and that retention is origin-scoped. That is genuine context beyond the annotations, though it does not say what happens when the window expires or how the recorded events are retrieved.

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?

Three dense sentences with no filler; the arming action and its scope lead, followed by origin behavior and recorded event types. Slightly more front-loading on what the caller gets back would improve it, but nothing is wasted.

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?

For a stateful arming tool with no output schema, the definition never explains what the caller receives when the window closes or how the recorded events are surfaced later. Duration and origin semantics are covered, but the end-to-end lifecycle expected of a session-arming tool is left implicit.

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 only 50%, with observation_ms and allowed_origins undocumented in the schema. The description compensates by explaining that the duration bounds the observation window and that an explicit origin list controls which origins may be retained, while defaulting to the target's current origin — meaningful semantics the schema lacks.

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: 'Arm a CDP observation window of the requested duration' and enumerates the recorded event categories (navigation, redirect, lifecycle, failure). That clearly separates it from execution- or runtime-oriented siblings, though it never names an alternative explicitly.

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 phrase 'while the user operates the page' implies the intended scenario — live, interactive observation rather than post-hoc capture — but there is no explicit when-to-use vs when-not guidance and no named alternative among observe_web_execution, inspect_web_network_capture, or compare_web_captures.

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