Skip to main content
Glama
Sign In
umbra

umbra

by lxchx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Har Record Start

har_record_start

Start recording paused requests and responses for a specific tab into a HAR-1.2 archive to capture network traffic for debugging.

Instructions

Begin buffering every paused req+resp into a HAR-1.2 archive (tab-scoped). Body capture is best-effort (skipped for fulfilled/blocked requests). Forces response-stage interception to capture status+body.

Ex: har_record_start('t0') → {"recording":true,"existing_entries":0}

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tab_id": "<tab_id>"
    },
    "name": "har_record_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
tab_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

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?

With no annotations, the description carries the full burden and does well: it discloses that body capture is best-effort and skipped for fulfilled/blocked requests, and that it 'forces response-stage interception'. It does not say where the archive lives, whether a har_record_stop/har_dump is required to retrieve it, or whether it conflicts with existing routes.

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 tightly-packed sentences with the core action front-loaded and an example call appended as a quick-shape reference. The interception side-effect sentence is a bit buried mid-paragraph but nothing is wasted.

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?

An output schema exists and the example confirms the return shape ({recording, existing_entries}), so return values need no prose. For a stateful recording tool the main remaining gap is lifecycle: how recording ends and how the HAR is retrieved, which the description leaves to sibling names.

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 0% for the single tab_id parameter, and the description only conveys that it is tab-scoped via the parenthetical and the example call har_record_start('t0'). That hints at the id format but does not define it or state what happens with an invalid/stale tab id.

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: 'Begin buffering every paused req+resp into a HAR-1.2 archive', plus the tab-scoped qualifier. It is clearly distinguishable from har_record_stop and har_dump in name, though the description never names those siblings 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?

Usage is only implied by 'Begin buffering' and the tab-scoped note; there is no statement of when an agent should choose this over route_captures, get_network_requests, or har_dump, nor what precondition 'paused' requests implies. The reader must infer the workflow.

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