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

Annotations only cover read-only/open-world; the description adds the things that actually change call behavior: millisecond stored reads versus a 10-30 second live fetch with refresh=true, what include_history unlocks and how far back (2023, Amazon US), and the hard scope limit (Amazon marketplaces only).

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?

Dense and front-loaded: payload first, then history toggle, then use cases, then latency and scope. Long but nearly every clause carries information; a little redundancy between the payload list and the include_history sentence.

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, yet the return payload is enumerated in enough detail (per-seller price/FBA/FBM/delivery, rating breakdown as percentages, sub-daily buy-box points) that an agent knows what it will get. Scope, latency, and freshness modes are all covered.

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; the description goes beyond it by explaining the barcode resolution path and precisely defining what include_history and refresh return in practice, which the schema descriptions only gesture at.

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?

Names a specific verb+resource ('full dossier for ONE Amazon product') and enumerates the payload (price, buy-box seller, all sellers, stock, BSR, rating breakdown, dimensions, history). The 'ONE' and 'by ASIN or by retail barcode' framing separates it from bulk_product_lookup and lookup_product_by_barcode at a glance.

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 concrete triggering situations ('what does this sell for now', 'who is on this listing', 'analyse this ASIN', a barcode from a supplier list) and distinguishes stored-vs-live via refresh. It stops short of naming the sibling alternatives (live_offers, asin_buybox_history, bulk_product_lookup) explicitly, so routing between this and those is left partly to inference.

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