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

Beyond the annotations it discloses cost ('uses one read per store that answers'), persistence ('saved in the user's Puley history'), and important result caveats: results follow each store's own ordering and may include accessories or other models, and shipping and tax are excluded. That is meaningful context the annotations (readOnlyHint false, openWorldHint true) do not convey. The phrase 'one read per store' sits slightly awkwardly against readOnlyHint=false, but it reads as a credit/consumption concept rather than a claim of read-only semantics, so it is not a real contradiction.

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?

It is front-loaded and every clause carries information, but the body is a single dense paragraph of country and store enumerations that is hard to scan. Much of the length is unavoidable given no enums in the schema, yet the content would be far more usable as a list rather than a run-on sentence.

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?

There is no output schema, and the description fills that gap by naming the returned fields (name, price in local currency, was-price, rating, reviews, stock, units sold, link). Combined with the region-to-store mapping and the per_store cap, an agent has everything needed to call it correctly and interpret the response.

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 0% and all four parameters are bare in the schema, so the description carries the full burden — and does: country is defined as two letters with default US plus an exhaustive per-country store mapping, stores is effectively enumerated with every accepted value and its region, per_store is bounded ('up to 12'), and query is implied by 'same product'. This is exactly the compensation the low coverage demands.

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 opening sentence states a specific verb and resource ('Search a country's big stores for the same product and list each store's results side by side, as a shopper there sees them') and enumerates the returned fields. It is clearly distinct from siblings like search_marketplace, best_sellers or resale_prices because the defining scope is cross-retailer price comparison within a country.

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 strong operational guidance: country drives which stores are queried, stores can 'narrow or add', per_store caps results, and specific use cases are called out (AliExpress for 'is it cheaper on AliExpress?', coles for unit prices, idealo as a price comparison). It stops short of naming an explicit alternative sibling or a 'do not use when' condition, so it is clear context without full routing.

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