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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds real behavioral context on top: pages may contain lists, videos, or both, tokens are opaque and prefix-inference is forbidden, and repeated requests may purchase data again. The cost disclosure is muddled, stating both "at least 10 Nexscope credits" and "1 credit per request", which leaves the agent unable to predict the charge.

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 first three sentences are well front-loaded and dense with useful detail, but the tail is pasted marketing boilerplate: "Amazon Shop Amazon Shop page API View Pricing", a duplicated product blurb, and a second, conflicting pricing statement. That noise both pads the definition and contradicts the earlier credit figure, so several sentences do not earn their place.

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 carries the return-value burden and does reasonably well: it names the storefront profile, product collections, and the video fields (id, title, thumbnail, attached ASINs). The remaining gap is the ambiguous credit cost and missing failure modes for a non-existent or private shop URL.

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 100% and the pageToken property description already says to pass it back unchanged, not to infer type from the prefix, and that a page may hold lists, videos, or both — so the description largely restates the schema. It does add one genuinely new fact (the initial request returns embedded videos without a pageToken), which earns the baseline rather than less.

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?

"Scrapes a creator's Amazon Shop page by URL, returning their storefront profile and product collections" names a specific verb, resource, and return scope, so the agent knows exactly what data it gets. It does not explicitly differentiate itself from nearby siblings (e.g. the tiktok_shop / shopify store lookups), which keeps it below a 5.

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 gives strong procedural guidance for pagination: the first call returns embedded videos without a token, and each returned pageToken must be passed back unchanged with the same shop URL. What it never states is when to choose this tool over alternative storefront/product tools, or what happens when a shop URL is invalid or the creator has no shop.

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