browser_launch

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

With no annotations, the description carries full burden and discloses many traits: anti-detection enabled by default, headless/headed modes, humanization, proxy support, persistent profiles, and auto-detection features. No contradictions found.

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 relatively long but well-structured: a summary line followed by a parameter list. Each line adds value; no obvious fluff. Slightly verbose but justified by parameter count.

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 (15 parameters, no output schema description), the description covers the tool's purpose, all parameters, and default behaviors. It omits potential error conditions or prerequisites, but is largely complete for agent usage.

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?

Schema coverage is 0%, so the description adds extensive meaning: it explains each parameter with defaults, examples, and behavior (e.g., viewport_width default varies by mode). This goes far beyond the schema's bare types and names.

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 'Launch a stealth CloakBrowser instance.' It specifies the verb 'Launch' and resource 'CloakBrowser instance', and distinguishes itself from sibling tools like navigate, click, etc. which are post-launch actions.

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 implies usage for starting a browser session, but does not explicitly state when to use this vs. alternatives (e.g., browser_new_page). No when-not-to-use or prerequisites are mentioned.

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