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

Annotations already declare readOnly, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: request-time freshness, 'every page' pagination depth, a 4-12 second latency expectation, and an 'Amazon marketplaces only' constraint. It stops short of describing rate limits or failure modes, hence a 4 rather than 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-loads the core purpose and then the usage routing, which is the right order. It is a dense two-sentence block, but nearly every clause (latency, marketplace restriction, returned fields) earns its place; the long enumeration of offer fields is the main reason it is not a 5.

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?

There is no output schema, so the description carries the return-value burden and does so thoroughly: per-offer fields (seller, seller id, price, shipping, condition, buy box, FBA/FBM/Amazon, Prime, ships-from, delivery promise, feedback) plus aggregates (buy-box winner, offer counts by fulfillment, whether Amazon sells it, lowest new and used prices). Combined with the latency and marketplace notes, an agent has everything needed to call and interpret it.

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 description coverage is 100%, so every parameter (zip, asin, barcode, include_used, marketplace_id) is already documented in the schema, including the marketplace enum values. The description adds no parameter-level syntax, defaults, or interaction rules (e.g. asin vs barcode precedence), so the baseline 3 is appropriate.

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 and resource ('LIVE Amazon offers for one product: every seller offering it right now') and names the data source ('Amazon's All offers view at request time'). It also names the sibling tools it is not (product_dossier, asin_buybox_history), so an agent can distinguish it without opening a 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?

Explicitly lists the triggering intents ('who sells a product right now, the current buy-box winner, the cheapest offer, or needs a fresh seller list before buying, sourcing or repricing') and routes historical needs to product_dossier or asin_buybox_history. 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.