Capture Annotated Screenshot

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

Annotations show `readOnlyHint=false`, consistent with writing locally. The description adds sensitivity warnings and local writing behavior, beyond annotations. No contradictions.

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 moderately concise but uses verbose phrases like 'full-profile visual diagnosis'. It front-loads the use case but could be tighter.

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?

Despite the output schema existing, the description lacks parameter details, leaving the agent uncertain how to construct valid inputs. Preconditions are stated but incomplete.

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 coverage, the description does not explain the purpose or usage of most parameters (e.g., `boxes`, `selector`, `fullPage`). It only mentions `acknowledgeRawCapture` as required, contradicting the optional schema.

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 captures annotated screenshots for visual diagnosis, distinguishing it from the unannotated sibling `browser_screenshot`. The verb 'capture' and resource 'annotated screenshot' are specific.

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 explicit preconditions (active page, `acknowledgeRawCapture: true`) and next steps. It implies the use case (full-profile visual diagnosis) but does not explicitly state when to avoid this tool in favor of alternatives.

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