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

Adds substantial context beyond the readOnly/non-destructive annotations: the data is a dated weekly sample rather than live, each keyword is observed roughly once a week, prices are in the marketplace's local currency, and marketplace coverage is still filling in for non-US/UK locales since 2026-10-30. These are exactly the staleness and coverage caveats an agent needs before citing the numbers. It stops short of describing pagination/limits on the returned product list, so not a 5.

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?

Front-loaded with the core definition, then usage, then caveats, then marketplace/currency — a sensible information order with no filler sentences. The opening sentence is very long and list-heavy, which makes it denser than ideal, but every clause carries information.

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?

No output schema exists, so the description carries the return-shape burden and does so by enumerating the payload components. Combined with cadence, staleness, currency and marketplace-coverage caveats, an agent has everything needed to call it correctly and interpret the results honestly.

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%, so the baseline is 3, but the description adds real meaning: keywords are constrained to head search terms from Amazon's own autocomplete rather than arbitrary long-tail strings, and marketplace_id output prices are denominated in that marketplace's currency. include_history is only indirectly hinted at via 'entered or left page 1 since the previous observation', so it isn't fully covered.

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+scope: 'Page 1 of Amazon search for a keyword as last OBSERVED', then enumerates the payload (organic order, buy-box seller, Sponsored Brands, Amazon's Choice, result count, brand/seller share, entrants/exits). It explicitly distinguishes itself from the sibling amazon_search_results by noting that tool reads the live page. An agent can route between the two without opening either schema.

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 an explicit 'Use for:' list of three concrete jobs (who sells on page 1, which brands/resellers dominate, who advertises) and an explicit when-not ('not live and not volume figures'), naming the alternative tool for live data and pointing volume questions away via the contrast with amazon_search_results. Nothing about selection is left to inference.

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