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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses the wrapped response shape {result: {results: [...]}} and instructs to unwrap both levels. It also warns about image_url quality and the resulting ugly link cards, and specifies a retry behavior for transient errors. These are substantive behavioral details that the annotations do not convey.

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 long but every sentence carries actionable information: the purpose, response unwrapping, image quality guidance, query construction tip, and error handling. It is structurally front-loaded with the core purpose before diving into nuances. A minor deduction for being somewhat dense and not splitting into clearly separated concerns, but it remains readable and efficient.

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 search tool with no output schema, the description is remarkably complete. It explains the response envelope, the meaning of commission_rate, the implications of image_url, how to craft queries for product pages, and a retry strategy for transient errors. The only untold details are the exact semantics of page and search_type, which are minor for a basic invocation and are partially inferable from the schema constraints. Overall, an agent can confidently call this tool correctly with the given description.

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 50% (q and filter have descriptions; page and search_type do not). The description adds valuable guidance for q, such as embedding the merchant product-URL path to surface product pages, and indirectly explains the filter behavior through the commission_rate discussion. But it never explains the purpose of page (max 10, pagination) or search_type (web vs image), leaving those parameters underspecified for an agent. It adds some value but does not fully compensate for the coverage gap.

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 clear, specific purpose: a commission-aware web search for products worth linking to. It names the resource (products) and the distinguishing feature (commission_rate), and its phrasing implicitly separates it from search_links and search_brands. The verb 'search' is explicit, and it immediately tells the agent why this tool exists.

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 says 'Prefer this over a plain web search', which provides a when-to-use directive. It also gives a concrete tip for surfacing product pages (embedding the product-URL path in the query) and a retry instruction for transient errors. However, it does not mention sibling search tools like split_search_brands or split_search_links or state when NOT to use this tool, so it stops short of a full exclusion list.

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