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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely useful behavior beyond them: per-call cost ($0.005 USDC via x402) and the shape of the result (differing-pixel count/percent plus a red-highlighted diff image). This is the kind of cost/return context annotations cannot carry, though it omits the paid share-link side effect of the store option.

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?

A single front-loaded sentence with the purpose first, then use case, outputs, and cost — no filler or redundancy. Slightly dense, but every clause carries information the schema and annotations do not.

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?

With no output schema, the description usefully characterizes the return value (counts, percent, diff image), which is good. However it leaves the input contract underspecified — how the two images are supplied and which inputs are mandatory — and does not surface the +$0.001 store behavior, leaving gaps for an 8-parameter tool.

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 coverage is only 38%: url_a, url_b, a_base64, b_base64 and no_image have no schema descriptions, and the description does not explain the URL-vs-base64 input alternatives or that one of each pair is required (0 required params listed). The only parameter it touches, fuzz tolerance, merely restates the schema's 'Colour tolerance percent, default 3'.

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?

States a specific verb+resource ('compare two images pixel by pixel') plus scope (screenshot visual regression) and names the return artifacts (diff pixel count/percent, red-highlighted diff image). This clearly separates it from the text-oriented text_diff and the single-image tools (image_classify, image_convert) without needing to name them.

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 parenthetical 'visual regression testing for screenshots' implies when the tool fits, but there is no explicit when-not guidance and no alternative named (e.g. text_diff, image_edit). An agent can infer the domain but must guess the selection boundary.

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