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

Annotations already cover readOnly/openWorld, so the description's real contribution is the credit cost ('Costs 3 credits') and the disclosure of what the payload contains, which helps an agent decide whether to spend. It stops short of noting rate limits, caching behavior (relevant given the cache_max_age param), or result volume.

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?

Three short sentences with the core scope front-loaded. The second sentence slightly restates the first ('All seller offers for a product' / 'Every offer on an Amazon listing') rather than adding new information, costing a little density but nothing harmful.

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 compensates by listing the returned fields, and it discloses the credit cost — the two things an agent most needs. Missing only practical invocation details such as pagination or how many offers typically come back.

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 80%, so parameters like asin, tld and the condition enum are already documented in the schema. The description adds only that condition is a dimension of each offer, not how the condition parameter filters results — 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?

The description names the resource and its scope explicitly: 'All seller offers for a product' with the returned fields enumerated (price, seller, condition, Prime eligibility, shipping). This separates it from amazon_product (product details) at a conceptual level, though it never names that sibling to make the split airtight.

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?

Usage is only implied: the phrase 'all seller offers for a product' hints you use it when you need competing seller pricing rather than catalog data. There is no explicit 'use this instead of amazon_product when...' statement, and the credit cost is stated without guidance on when that trade-off is worth it.

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