Skip to main content
Glama
frsorrentino

Chrome Bridge

by frsorrentino
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

manage_downloads

Manage browser downloads: list active downloads, start new ones, and wait for completion. Reports status, including when Chrome prompts for a save location.

Instructions

List downloads, start one, or wait for the newest to finish. Files land in the browser Downloads folder, not on the server. download reports the real state: with Chrome set to ask where to save, it comes back waiting_for_user — bytes fetched, nothing moves until someone picks a destination.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoWhat to download (action=download); sent with the session cookies of its origin
limitNoMax download entries returned, newest first
actionYesdownload fetches with the browser cookies and reports the real state; wait_for_complete blocks until the newest finishes
timeoutNoMax ms (wait_for_complete)
filenameNoRelative path inside the Downloads folder (action=download)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.16.1
    • changedInput schema / properties / action / description
      Previous value: -"download fetches with the browser cookie jar and reports the real state; wait_for_complete blocks until the newest finishes"New value: +"download fetches with the browser cookies and reports the real state; wait_for_complete blocks until the newest finishes"
  2. Changed4 schema fields changedv1.15.0
    • changedInput schema / properties / action / description
      Previous value: -"wait_for_complete blocks until the newest download finishes or times out"New value: +"download fetches with the browser cookie jar and reports the real state; wait_for_complete blocks until the newest finishes"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "list",
-  "wait_for_complete"
-]New value: +[
+  "list",
+  "wait_for_complete",
+  "download"
+]
    • addedInput schema / properties / filename
      Added value: +{
+  "description": "Relative path inside the Downloads folder (action=download)",
+  "type": "string"
+}
    • addedInput schema / properties / url
      Added value: +{
+  "description": "What to download (action=download); sent with the session cookies of its origin",
+  "type": "string"
+}
  3. Changed2 schema fields changedv1.10.0
    • addedInput schema / properties / action / description
      Added value: +"wait_for_complete blocks until the newest download finishes or times out"
    • addedInput schema / properties / limit / description
      Added value: +"Max download entries returned, newest first"
  4. First observedv1.8.0

TDQS

A4.4/5.0
Behavior5/5

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

The description discloses important side effects and real-world behavior: downloads are saved to the browser's Downloads folder, the tool reports the actual state, and a download may return waiting_for_user if Chrome asks for a destination. This goes beyond the minimal annotations and gives the agent useful runtime expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, leading with the three primary operations. It avoids unnecessary detail and each sentence contributes meaningful information about behavior or side effects.

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?

The description covers the tool's core actions, storage location, and state-reporting behavior, which is enough for basic use. It does not explicitly describe the return values for list or wait_for_complete, but given the simple schema and annotations, this is a minor gap rather than a critical omission.

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?

The JSON schema already provides 100% coverage of all parameters with descriptions. The tool description mostly restates the action enum behavior and adds little new meaning about the parameters themselves, so it provides only marginal additional value beyond the schema.

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?

The description clearly identifies the tool's purpose: list downloads, start one, or wait for completion. It distinguishes this from server-side file operations by explicitly stating files land in the browser Downloads folder, and it conveys the download-state reporting behavior.

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?

The description explains the practical context of use, including where files are stored and what happens when the browser is configured to ask for a save location. It does not explicitly name alternative sibling tools, but the 'not on the server' note helps an agent choose this over server-side file operations.

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