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

Annotations already declare readOnlyHint and openWorldHint, so safety and open-web scope are covered. The description adds real context the annotations don't: results are scoped to the end user's marketplace, and marketplace+locale must always be supplied together. It says nothing about result volume, the purpose of limit, or failure behavior when a marketplace is unsupported, so it is additive but partial.

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?

Two tight sentences with the core action front-loaded and the mandatory-parameter constraint immediately after. "OpenAPI: searchAmazon" is an internal routing hint of marginal value to an agent, which is the only wasted fragment.

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 7-parameter tool with no output schema and two enums (occasion, giftCategory) whose effect on results is unexplained, the description does the minimum. An agent knows how to call it but not what the optional gift-filtering parameters actually change, nor when to prefer a sibling tool.

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 57%, and the schema already documents q, locale, marketplace, and dietaryNotes with examples. The description reinforces the marketplace/locale pairing but adds nothing about occasion, giftCategory, or limit beyond their enum values. Baseline 3 is appropriate for a mid-coverage 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 and resource: "Search Amazon for hostess / dinner-party gifts on the user's marketplace." That is more specific than a bare "search" and scopes the domain (gift/entertainment shopping), which separates it from get_catalog or resolve_product. It stops short of naming a sibling it is explicitly not, so a 4 rather than a 5.

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 only directive is "ALWAYS pass marketplace + locale," which is parameter hygiene, not when-to-use guidance. With siblings like get_catalog and resolve_product in the same family, the description never says when to search here versus browsing a catalog or resolving a known product.

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