Skip to main content
Glama

har_export

Export a tab's listed network requests to a HAR 1.2 file for attaching to bug reports; optionally include response bodies, while cookie and authorization values are redacted.

Instructions

Save the requests read_network_requests lists for a tab as a HAR 1.2 file, e.g. to attach to a bug report.

It goes in zenpilot's har folder, or at path: an absolute path ending in .har, in zenpilot's state
folder or the temp folder. Existing files are never overwritten. Response bodies are left out unless
include_bodies, and cut at 100 KB each. Cookie and authorization header values show as [redacted].

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "har_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
tab_idNo
include_bodiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it names the destination folders, the .har extension requirement, the absolute-path constraint, that existing files are never overwritten, that bodies are omitted by default and truncated at 100 KB, and that cookie/authorization values are redacted. These are exactly the non-obvious safety and data-loss facts an agent needs before writing a file.

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?

Front-loaded with purpose, then constraints, with no filler. The middle sentence about the har folder versus an explicit path is somewhat convoluted in its clause nesting, costing a little readability, but every sentence carries information.

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?

For a three-parameter write tool with no annotations and no output schema, the definition covers location rules, overwrite safety, body handling, and redaction. It would be complete if it said what the tool returns (e.g. the written file path) and how tab_id defaults.

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 0%, so the description must compensate, and it explains two of three parameters in real detail: path gets format and allowed-location constraints, include_bodies gets default behavior plus a size cap. tab_id is only obliquely covered ('for a tab') with no statement of what happens when it is omitted, leaving one parameter under-specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Save ... as a HAR 1.2 file') and ties the input explicitly to the sibling that produces it ('the requests read_network_requests lists'), so an agent can tell this is the export step for captured network traffic rather than another read tool.

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?

Gives a concrete motivating use case ('e.g. to attach to a bug report') and implies the prerequisite that traffic must first be captured via read_network_requests. It does not state when not to use it or what happens if nothing has been captured, but no sibling competes for this job.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.