start_browser

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

With no annotations, the description carries the full burden, and it does disclose useful behavior: the tool is optional, Chrome auto-starts by default, and this tool exists for customization. However, it does not state what happens if a browser session is already open, such as whether the existing session is reused, replaced, or left untouched. That gap leaves an important behavioral trait undisclosed.

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?

Two sentences deliver all essential information without waste. The optionality is stated up front, followed by the specific customization use case, making the purpose immediately clear.

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?

For a low-complexity tool with zero required parameters, defaults, and no output schema, the description covers purpose, optionality, and parameter intent well. The main missing piece is the effect on an already-running browser session, but overall the agent has enough context to invoke the tool correctly in common scenarios.

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 description coverage is only 33%, but the description compensates by mapping each customization to the relevant parameter: 'choose Firefox' maps to browser, 'enable headless mode' maps to headless, and 'set a custom window size' maps to window_size. The schema also provides defaults and an enum for browser, so the agent has enough semantic grounding for all three parameters.

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 states a clear verb and resource: 'Start a browser session.' It then explains the tool's specific role by noting it is optional and used to select Firefox, headless mode, or a custom window size, which differentiates it from auto-start behavior and other browser tools like close_browser.

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 explicitly says when to use the tool: 'any tool will auto-start Chrome if no browser is open,' so the agent knows this call is only needed for specific customizations. It lists the exact cases where start_browser is appropriate: choosing Firefox, enabling headless mode, or setting a custom window size. This is clear when-to-use guidance with implied when-not-to-use.

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