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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely new context: results are PA-API products when configured, otherwise gaming-filtered deep-link cards. That fallback/output-mode disclosure is exactly the kind of behavior an agent cannot infer from annotations, though nothing is said about rate limits, empty-result behavior, or pagination.

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 tight sentences, front-loaded with the action and the return-mode caveat. The trailing 'OpenAPI: searchAmazon' is a minor low-value artifact but costs little.

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 7 params, no output schema, and a modifier parameter (budgetBand) documented nowhere, the description covers the return shape and fallback well but leaves filtering parameters opaque. An agent could call it, but only by guessing at genre/platform/budgetBand semantics.

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 only 43%, so the description should carry more weight, but it only repeats that marketplace and locale are required (already in the required array and schema descriptions). genre, platform, limit, and especially budgetBand (no schema description at all) get no explanation of format or effect.

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 gaming gear') and scopes it to the user's marketplace, which separates it from mutation siblings like add_item and create_wishlist. It does not explicitly distinguish itself from resolve_product or get_catalog, so the agent must infer the search-vs-lookup boundary.

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?

'ALWAYS pass marketplace + locale' is invocation guidance but not selection guidance. Nothing says when to prefer this over resolve_product (single known item) or get_catalog, so the when-to-use decision is only implied by the word 'Search'.

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