Capture Screenshot

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

Annotations provide minimal behavioral info (readOnlyHint=false, openWorldHint=true). The description adds critical context: screenshots may capture sensitive data and are written locally. It also hints at region selection behavior. This is good but could mention if it waits for network idle or page load.

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 two sentences, front-loading the use case and preconditions. Every sentence adds value. However, it could be structured into bullet points for clarity, but conciseness is not sacrificed.

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 tool's moderate complexity (4 parameters, no required ones, output schema exists), the description covers usage and sensitivity but misses parameter details. The output schema relieves some burden for return values, but the parameter ambiguity lowers completeness.

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 0%, so the description must explain parameters. It mentions acknowledgeRawCapture as a precondition and region selection, but does not define parameters like 'selector' (CSS selector? Coordinates?), 'outputPath' (path format?), or 'fullPage' (true/false behavior). This lack of detail impedes correct invocation.

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 purpose: capturing visual evidence for layout, overlays, rendering, or interaction results. It distinguishes from siblings like browser_snapshot and browser_screenshot_annotated by emphasizing visual evidence for layout analysis.

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), guidance on when to select a region vs full page, and suggests next steps (targeted DOM or trace inspection). It also notes sensitivity, giving an exclusionary condition for alternative tools.

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