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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint=false and destructiveHint=false. The description adds genuinely new behavioral context: API key requirement and a per-call batch ceiling of 50 products. It does not explain what idempotentHint=false means in practice (e.g. re-running re-researches/refreshes), which is the one annotation worth unpacking.

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 audience and scope lead the sentence, which is the right front-loading, and there is no filler. It is one sprawling sentence with nested parentheses ('(standards it takes and provides, numeric limits, evidence level, freshness)', '(SKU with title, URL or GTIN)') that packs a lot into a single breath and slightly resists parsing.

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 a title, a rich annotation set, and an output schema already in place, the description carries a lighter burden, and it covers audience, auth, batch limits, and output character well. The notable hole is that the `research` behavior (default on, up to 10 uncatalogued items researched from the manufacturer's page) appears only in the schema, so an agent reading the description alone would miss a meaningful mode.

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 50%. The description names only three of the six item fields (title, URL, GTIN) and adds no format detail, and it omits the `research` parameter entirely — arguably the most consequential one, since it governs whether unknown items trigger manufacturer-page research. With half the schema documented, the baseline 3 is appropriate.

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 ('enrich a product catalog'), names the audience (retailers and marketplaces), and pins down both the input shape (SKU with title, URL or GTIN, up to 50 per call) and the output (compatibility attributes: standards taken/provided, numeric limits, evidence level, freshness). This is specific enough to distinguish it from siblings like check_compatibility or resolve_product.

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 establishes the audience and scenario ('ready to add to a product feed or UCP catalog so agents can match it to what shoppers own'), which implies batch enrichment use. However, it never states when to reach for this tool versus the many sibling tools, nor any exclusions, so the routing is left to inference.

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