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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds genuinely useful context: results come from UCP-verified stores, the country's big retailers, and Shopify cross-store search, and include 'what they let agents do' — i.e., per-store agent capabilities. It stops short of describing result ordering, coverage limits, or behavior when the country is unknown.

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 sourcing information is front-loaded in the first clause, and the example at the end is compact and directly actionable. The middle section is a slightly run-on comma pile ('stores verified for AI agents (UCP), the country's big retailers and what they let agents do, Shopify cross-store search'), but nothing is redundant enough to cut outright.

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 search tool with no output schema, the description does enough: it names the data sources, signals that results carry per-store agent capabilities, and shows a sample call. The remaining gap is that an agent still can't predict the result shape (store fields, ranking, or meaning of the limit default) without invoking the tool.

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 100%, so all four parameters (limit, query, country, agent_checkout_only) are already documented in the schema, making 3 the baseline. The description reinforces 'Any language' for query and the worked example shows query+country usage, but it adds no semantics for limit or agent_checkout_only and doesn't explain what 'UCP agent checkout only' filters out.

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 concrete verb and resource: find stores where a product can be bought in a given country, and it enumerates the three data sources (UCP-verified stores, national big retailers, Shopify cross-store search). An agent can immediately tell this is a store-discovery lookup rather than a shop-specific check, although the sibling check_shop is never named as the contrasting tool.

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?

Usage is only implied by the word 'Where to buy' — an agent infers it should call this when it needs purchase options. There is no explicit when/when-not guidance, no indication of how this differs from check_shop or check_reliability, and no advice on when to set agent_checkout_only versus leaving it unset.

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