browser_screenshot

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

With no annotations, the description must carry the behavioral burden. It does disclose a genuine trait beyond structure — that the capture may contain sensitive page content — but it omits scope (viewport vs full page), return format, and any session/state prerequisites.

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 short sentences, front-loaded with the action and followed by the caveat. Nothing is padded or redundant.

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 no-param, no-annotation, no-output-schema tool, the definition leaves the return channel unexplained — whether the agent receives image data, a path, or a handle — which an agent needs in order to consume the result. The sensitivity warning is a useful addition but does not close that gap.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The reference to 'bounds in the snapshot' is a cross-tool hint rather than a parameter explanation.

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?

States a specific verb and resource: 'Capture the current page as an image.' The word 'current page' implicitly separates it from browser_element_screenshot, but it never names that sibling or browser_snapshot explicitly, so the differentiation is only inferable.

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 second sentence implies when a screenshot is useful ('to identify image-only controls' via bounds in the snapshot), which is real usage context, but there is no explicit when-to-use/when-not framing and no named alternative such as browser_snapshot or browser_element_screenshot.

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