launch_browser

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

No annotations exist, so the description fully bears responsibility. It discloses behavioral traits: attach mode cannot inject host/os font-fallback shim, close_browser() only disconnects in attach mode, and that enable_trace requires a custom browser build. It does not detail side effects like resource consumption or authentication needs, but covers key behaviors.

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

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

The description is well-structured with 'Args:' and 'Returns:' sections, and each parameter is documented concisely. It is somewhat lengthy but every sentence adds value. Minor redundancy (e.g., repeating 'attach' mode behavior) could be tightened, but overall effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (10 optional parameters, no output schema), the description is complete: it covers both modes, parameter dependencies, return type (dict with status/config/page list), and mentions related tools (close_browser, trace_property_access). An agent can confidently invoke this tool based solely on the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must explain all 10 parameters. It does so thoroughly: headless, os_type, locale, proxy, humanize, geoip, block_images, block_webrtc, enable_trace, and ws_endpoint each have clear descriptions of purpose, defaults, and special notes (e.g., geoip auto-infers from proxy, ws_endpoint overrides others). This fully compensates for the schema gap.

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

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

The description clearly states the tool's purpose: 'Launch the Camoufox anti-detection browser, or attach to a running one.' It uses a specific verb ('launch'/'attach') and resource ('Camoufox browser'), distinguishing it from sibling tools like navigate or take_screenshot.

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

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

The description provides clear guidance on when to use launch vs attach mode via the ws_endpoint parameter, noting that attach ignores other launch args. It mentions server startup command and fingerprint considerations. However, it lacks explicit exclusions or alternatives to using this tool versus other browsers/setup methods.

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