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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is established. The description adds valuable behavioral context beyond that: it reads already-collected results rather than running a live scan, and ASINs not yet scanned show 0 sources / never-scanned. These are non-obvious behaviors that would affect how an agent interprets results, and they are not present in the annotations.

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 information-dense. It front-loads the core purpose and read-only caveat in the first sentence, then lists return fields, then gives use cases and the alternative tool. Every sentence contributes something useful, though a few metrics in the return list could arguably be trimmed without losing crucial meaning.

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 no output schema, so the detailed return-field list in the description is essential and well provided. It covers the key behavioral caveats, including never-scanned ASINs and the fact that no live scan runs. It also handles routing against a sibling tool. Minor gaps include pagination/default-limit behavior and how multiple filters interact, but for a read-only aggregation tool this is largely complete.

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 56%, and the description itself does not add parameter-level explanations. However, most parameter names are self-explanatory (limit, domain_contains, min_cheapest_web_price, violations_only) and several have schema descriptions. The description's output-focused overview helps interpret what sort and filter parameters control, but it does not fully compensate for the undocumented parameters. This is adequate but not outstanding.

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 precise verb and resource: it bulk-returns web-wide price and MAP findings across the entire watchlist in one call. It clearly distinguishes itself from the live single-product tool by explicitly saying it reads already-collected results and does not run a live scan, and it names find_product_across_web as the alternative. The purpose is unmistakable even before looking at the schema.

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 gives explicit use cases in quoted natural-language examples: 'where is my whole watchlist cheaper off Amazon', 'web-wide MAP across everything I track', and 'which tracked products are undercut on the open web'. It also provides a direct exclusion: for a live single-product cross-retailer check, use find_product_across_web instead. This is model routing guidance at its best.

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