softglaze-browser-mcp

Overview Schema Source Related Servers Discussions Admin

Open a URL in a profile

page_navigate

Opens an HTTP(S) URL in a running Chromium profile’s main tab through its proxy, waits for load, and returns the final URL and title; requires one-time approval per profile.

Instructions

Opens an http(s) URL in a running Chromium profile's main tab, through its proxy, and waits for the page to load. Returns the final URL and title. Asks the user once per profile (Allow for 1 hour covers all page tools on it).

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": {
      "profileId": "<profileId>",
      "url": "<url>"
    },
    "name": "page_navigate"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`profileId`	Yes
`timeoutMs`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Goes well beyond the annotations: it discloses that navigation happens in the main tab, routes through the profile's proxy, blocks until load completes, returns the final URL and title, and triggers a per-profile user consent prompt with a one-hour window. It does not state what happens to the previously loaded page content or how load failures/timeouts surface.

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 tight sentences, front-loaded with the action and scope, followed by return values and then the consent caveat. The parenthetical about the one-hour Allow window is slightly compressed but still earns its place by preventing repeated permission confusion.

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?

With no output schema, the description usefully states the return values (final URL and title), and it covers the consent and proxy behavior an agent needs before calling. The main gap is the undocumented timeoutMs parameter and any error/timeout behavior.

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%, so the description carries the burden; it adds real meaning for two parameters by constraining the URL to http(s) and requiring a running profile. The third parameter, timeoutMs, is never mentioned in the description or schema, leaving its semantics (and the 45s cap) undocumented.

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 ('Opens') plus the exact resource ('an http(s) URL in a running Chromium profile's main tab, through its proxy') and the completion condition ('waits for the page to load'). This clearly separates it from sibling page_* tools that act on an already-loaded page.

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?

Implies the prerequisite that the profile must already be running and notes the consent prompt cadence ('once per profile ... 1 hour covers all page tools'), which tells the agent how navigation interacts with other page tools. It does not explicitly name alternatives (e.g., page_snapshot or page_extract_text for reading a page), so no exclusion guidance is given.

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