Skip to main content
Glama
frsorrentino

Chrome Bridge

by frsorrentino
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

session_record

Record browser session commands or watch user actions as replayable JSONL, then export the flow as a Playwright test. Use it to repeat a flow or hand over a procedure.

Instructions

Record the commands of this session as a replayable jsonl (chrome-bridge replay --file ); observe what the user does in a tab ("watch how I do it") into the same format plus a readable procedure, never recording sensitive values; export a recording as a Playwright test for CI. Replays target the tab they navigate. Use it for a flow to repeat or a procedure to hand over; for one check now, assert.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoRequired for start, observe and export (recording name, or a .jsonl path)
actionYesstart records this session; observe records what the USER does; stop writes the file; export makes a Playwright test
tab_idNoTarget tab; omitted = last tab navigated in this session, else the active one
valuesNoobserve: record values of non-sensitive fields instead of {{field}} placeholders
save_toNoAbsolute path: write the exported .spec.ts there and return the path instead of the content

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.16.1
    • changedInput schema / properties / action / description
      Previous value: -"start begins recording, stop writes the file and returns its path"New value: +"start records this session; observe records what the USER does; stop writes the file; export makes a Playwright test"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "start",
-  "stop",
-  "status",
-  "list"
-]New value: +[
+  "start",
+  "stop",
+  "status",
+  "list",
+  "export",
+  "observe"
+]
    • changedInput schema / properties / name / description
      Previous value: -"Required for start"New value: +"Required for start, observe and export (recording name, or a .jsonl path)"
    • addedInput schema / properties / save_to
      Added value: +{
+  "description": "Absolute path: write the exported .spec.ts there and return the path instead of the content",
+  "type": "string"
+}
    • addedInput schema / properties / tab_id
      Added value: +{
+  "description": "Target tab; omitted = last tab navigated in this session, else the active one",
+  "type": "number"
+}
    • addedInput schema / properties / values
      Added value: +{
+  "default": false,
+  "description": "observe: record values of non-sensitive fields instead of {{field}} placeholders",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.10.0
    • addedInput schema / properties / action / description
      Added value: +"start begins recording, stop writes the file and returns its path"
  3. First observedv1.8.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare it writes (readOnlyHint=false) and is non-destructive, but the description adds genuinely useful behavioral context beyond them: 'never recording sensitive values', the replay targeting rule ('Replays target the tab they navigate'), and the replay CLI form. It does not mention permissions or persistence side effects, keeping it short of a 5.

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?

The primary purpose is front-loaded and each clause carries information (modes, format, privacy, routing rule, alternative). The semicolon-chained style is dense and slightly hard to parse, but there is little pure filler.

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 no output schema and a six-value action enum, the description should say more about what status and list return. It explains the export return behavior only indirectly and leaves the non-mutating modes' outputs opaque, so it is adequate but incomplete for a multi-mode tool.

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 100%, so the schema already documents every parameter including the action enum and save_to behavior. The description adds little parameter-level detail (only the replay --file hint), so baseline 3 is appropriate.

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 names a specific verb+resource (record session commands as replayable jsonl) and enumerates its three modes: record, observe, and export to Playwright. It even distinguishes itself from the sibling 'assert' tool. It loses a point only because the scope sprawls across three loosely-related capabilities, making the single 'purpose' slightly diffuse.

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

Usage Guidelines4/5

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

It gives explicit selection criteria ('for a flow to repeat or a procedure to hand over') and names the alternative for the opposite case ('for one check now, assert'). This is close to a full when/when-not rule, though it doesn't cover other exclusions or prerequisites.

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