compare_screenshots

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

No annotations are provided, so the description must fully disclose behavioral traits. It states the tool uses pixelmatch and returns results, but omits important details: whether it modifies any state, file size limitations, or required image properties (e.g., same resolution). This leaves behavioral ambiguity.

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, each earning its place: first states the action and method, second lists outputs. No filler or redundancy. Highly efficient and front-loaded.

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 4 parameters, no output schema, and no annotations, the description partially covers usage. It explains the return values (percentage, pixel count, diff image) but lacks prerequisites (e.g., images must be same size) or format of the diff image (base64 implied but not stated). Adequate but with clear gaps.

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?

Input schema coverage is 100% and already parametrizes beforeImage, afterImage, threshold, includeDiffImage. The description adds context (pixelmatch, return values) but does not enhance understanding of parameters beyond the schema. Baseline score of 3 is appropriate given high schema coverage.

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 explicitly states it compares two screenshots pixel-by-pixel using pixelmatch, and lists the outputs (match percentage, mismatched pixel count, diff image). This clearly distinguishes it from sibling tools like diff_page_source (text-based) and compare_snapshots (likely different granularity).

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?

No guidance on when to use this tool versus alternatives. While the name implies pixel-level comparison, the description does not explicitly address trade-offs with compare_snapshots or other visual comparison tools, nor does it state prerequisites (e.g., same image dimensions).

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