browser_screenshot

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

Annotations already declare readOnlyHint=true, lowering the bar. The description adds a valuable warning that page content is untrusted, which is critical behavioral context for an agent using the screenshot to make decisions. It also clarifies that it captures the current viewport, defining the scope of the operation.

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 exactly two sentences with zero fluff. The first sentence delivers purpose and usage in one compact clause; the second delivers a critical trust warning. Information is front-loaded and every word earns its place.

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 zero-param, no-output-schema tool, the description covers purpose, usage, and a security warning. It doesn't specify output format (e.g., image path vs. base64), but for a screenshot this is often implicit or handled by the agent's runtime. It provides enough for a correct invocation.

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 has zero parameters, so the schema is trivial and the description need not explain parameters. Baseline for no-param tools is 4; the description correctly avoids adding meaningless detail about nonexistent inputs.

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 the tool inspects the current viewport, which clearly implies a screenshot. It also ties the purpose to a workflow step ('before choosing click coordinates'), distinguishing it from sibling interaction tools like browser_click. The verb 'inspect' is slightly indirect but the meaning is unambiguous given the tool name.

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?

Explicitly instructs when to use it: before choosing click coordinates, framing it as a reconnaissance step. While it doesn't name alternatives like browser_click, it gives a clear contextual trigger that implies this is the visual verification tool. This is sufficient guidance for an agent to decide when to invoke it.

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