Compare replica against original

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

The description adds behavioral details beyond annotations: animations frozen, same viewport, pixel-diff approach, and output contents. Annotations already declare read-only/idempotent hints, so the bar is lower; the description complements rather than repeats. It does not mention potential network access or timeout behaviors, but those are covered by parameters.

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?

Three compact sentences: action, output, and usage loop. Everything earns its place and the main purpose is front-loaded. No fluff or redundancy.

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 tool with 15 parameters and an output schema, the description covers the core workflow and return values. It is complete enough to select and invoke correctly for the intended loop-based iteration. The output schema handles detailed return structure, so the description need not elaborate further.

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 100% with detailed parameter descriptions. The description adds minimal new parameter semantics; it mentions 'local file or URL' which aligns with replicaPath/replicaUrl, but otherwise the schema carries the burden. Baseline 3 is appropriate.

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 specific verb+resource: 'Screenshot the original website and a replica... then pixel-diff them.' It clearly distinguishes from siblings like capture_screenshot by focusing on comparison and diffing. Returns are explicitly listed (match percentage, worst-matching regions, visual diff image).

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?

Provides a clear usage loop: 'Use in a loop: build, compare, fix the worst regions, repeat.' This tells the agent when to use the tool in an iterative workflow. It does not explicitly name alternative tools or when not to use it, but the context is strong.

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