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

Although annotations already establish read-only, non-destructive, open-world behavior, the description adds substantial operational context: no create/update side effects, Amazon API dependency, rate-limit behavior with HTTP 429 and TOO_MANY_REQUESTS, no retry on rate limit, and instructions to retain prior items and retry only the failed page with the same nextToken.

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 front-loaded with the core read-only POST purpose and the key source-selection rule. It is necessarily detailed for a complex recommendation workflow, though a few sentences, such as the general note about retrieval from Amazon Ads recommendation APIs, are somewhat redundant with earlier context.

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?

The tool has an output schema, rich annotations, and 100% schema description coverage, so the description does not need to explain return values in detail. It still covers the critical disambiguation, supported recommendation modes, pagination/rate-limit behavior, and workflow handoff to bid recommendations, making it complete for correct invocation.

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 schema already documents all nine parameters. The description adds useful semantic constraints beyond the schema, especially the exactly-one-source rule, the relationship between adGroupId and server-resolved context, adProduct coupling with asins, and the T00020 limitation for Sponsored Display ASIN product recommendations.

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 states a specific verb and resource: read-only retrieval of Amazon-recommended keyword or ASIN targeting candidates before targeting entities are created. It clearly distinguishes this tool from sibling tools such as query_advertising_targets, query_advertising_bid_recommendations, and the apply/prepare targeting tools by framing it as the recommendation-discovery step.

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?

It gives explicit usage sequencing: use this tool first when the customer has not selected targeting candidates, then pass selected targeting objects to query_advertising_bid_recommendations before creation. It also states the exactly-one-source rule and the ad-product-specific supported recommendation types.

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