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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the 500-per-store catalogue ceiling, that prices are only as of last_seen_at, that 'accepts offers' is true only for stores in the live list, that price-match is only yes/no once a person verified the policy, and that coverage is partial. These caveats materially change how an agent should interpret results.

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?

One dense paragraph with the action front-loaded, followed by return contents, filters, and caveats. Very little waste, though the long parenthetical verification clauses make it heavier to scan than necessary.

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 no output schema, the description still enumerates the returned fields (price, store page, last_seen_at, accepts_offers, price_match) so an agent knows what to expect, and the staleness and coverage caveats cover the remaining risk of misuse.

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 the baseline is 3, but the description adds real meaning: it explains that price_match only reflects verified policies and that accepts_offers is gated on a live list, and it frames country/price_max as filters over store currency and lowest price. The query parameter's semantics are left to the schema.

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?

States a specific verb and resource ('Searches the products the Registry has pulled from its retailers' own catalogues') and enumerates what each hit contains, which distinguishes it from siblings like retailers_that_price_match that return stores rather than products. The scope limit (Shopify stores, up to 500 products each) further pins down what it does.

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?

Gives clear context for calling it: searching catalogues by country, price ceiling, offers-only, or verified price-match. It also sets expectations ('confirm on the product page before quoting') and pre-empts a false negative ('an empty result is not a no'), but it names no sibling alternative for when a different tool is the right pick.

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