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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description complements them with valuable behavioral detail: each page costs 1 credit, one page typically returns 20-40 products, response includes a refinements field, and results can include sponsored items. It also discloses how to avoid unnecessary pages via sort_by and exclude_sponsored. This goes well beyond the annotations and gives the agent accurate expectations about cost and result shape.

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?

The description is organized into three focused paragraphs: core purpose and return values, when to use it, and operational guidance. Every sentence contributes useful information without redundancy. The most important distinguishing instruction ('use get_product_detail directly' for ASINs) is placed prominently, and the cost/credit note is front-loaded in the operational guidance.

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?

For a tool with 10 parameters, rich enum options, and no output schema, the description covers all essential decision points: search method (keyword vs URL), parameter strategy (sorting, sponsored filtering, refinements), credit cost, page size, and alternative tool routing. It even explains how to obtain valid refinement IDs, which is critical for correct invocation. No meaningful gap remains for an agent to select and call this tool correctly.

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 the baseline is 3, but the description adds meaningful parameter-level guidance beyond the schema. It explains that valid refinement IDs must be discovered by reading the refinements field of a previous search, that sort_by and exclude_sponsored should be preferred over fetching more pages, and that domain should match the user's market. These insights help the agent choose parameter values wisely.

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 opens with a specific verb and resource: 'Search Amazon by keyword or a full search/category URL and get structured product listings.' It enumerates exact output fields (ASIN, title, price, rating, review count, Prime status, badges) and explicitly names the sibling differentiation ('do NOT search — use get_product_detail directly'). This leaves no ambiguity about what the tool does or how it differs from related tools.

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?

The description explicitly states when to use the tool: 'Use this tool for market research, keyword analysis, and product discovery.' It also gives a clear exclusion: 'If the user already has an ASIN or product URL, do NOT search — use get_product_detail directly.' Additionally, it provides practical guidance on filtering and pagination, making the selection criteria complete and actionable.

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