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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description substantially extends them: it reads Webotee's store (re-read ~14 days), never fetches Amazon live, returns not_yet_tracked for unknown sellers, restricts feedback text ('never a buyer's name or text'), and notes the business block is null on au/ca. That is real behavioral context an agent cannot get from the annotations.

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 and organized into purpose, RETURNS list, usage trigger, and caveats. The RETURNS sentence is long and dense, but each clause maps to a distinct return element an agent needs; little is padding, though it could be tightened.

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 must carry the return contract, and it does exhaustively (rating, counts, feedback windows, histogram, recent entries, business block, tracking, optional history series). Freshness, live-vs-stored sourcing, and the not_yet_tracked failure mode are all stated.

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 the resolution semantics between the two identifier options ('the A... code in /sp?seller=... or the seller_id on an offer' vs the name the other tools use) and how include_history/history_points interact. It clarifies which identifier to pick in context rather than merely restating the schema.

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 ('The stored Amazon SELLER PROFILE for one seller') and enumerates exactly what comes back (rating, feedback, histogram, business block, tracking). It explicitly distinguishes itself from the sibling operator_* tools by scope: profile/identity here, 'what a seller SELLS' there.

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?

Gives an explicit USE WHEN trigger ('who a seller is, how it is rated, whether its rating moved, or the legal entity behind a storefront') plus a named alternative for the adjacent need ('For what a seller SELLS use the operator_* tools'). Both when-to-use and when-to-use-something-else are covered.

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