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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavioral value beyond them: it discloses the visibility filter — hidden products, unchecked or paused manufacturers, and archived versions are never returned — and that documents are returned as the public page shows them. It does not mention rate limits or pagination, which keeps it off a 5.

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?

Two sentences, no filler, with the input forms front-loaded before the return behavior. Every clause carries information: input types, return contents, and visibility exclusions.

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 read-only, two-parameter tool with no output schema, the description covers the accepted inputs, the shape of the response (identifiers plus every current document), and the filtering rules. "Identifiers" remains somewhat abstract and no response structure is sketched, but the referenced "public product page" gives an agent a reliable mental model.

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 100%, so 3 is the baseline. The description goes slightly beyond the schema by giving the concrete URI shapes (/q/<code> with a 7-character code, /01/<gtin> as GS1 Digital Link), which clarifies how a pasted URL maps onto the "product" parameter rather than merely repeating the accepted-type list.

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 uses a specific verb ("Resolves") and enumerates the exact input forms it accepts — QR link or 7-char code, GTIN, GS1 Digital Link, product page URL, and "manufacturer-slug/product-slug" — then states what it returns ("the public product" with its identifiers and current documents). This makes it clearly distinguishable from search_products, get_qr_link, and get_my_product without opening any 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?

"What is printed on a label or pasted from a browser" gives a concrete triggering context for the tool, and the accepted-input list effectively tells the agent when this tool applies rather than a sibling. It stops short of explicit exclusions or naming an alternative (e.g. use search_products when you only have a name), so it is strong context without full routing guidance.

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