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

Goes well past the annotations, which already cover read-only/idempotent/non-destructive: it discloses that typos are corrected per site, that results include URL and manufacturer list price, that the offer summary is locale-market bound (shops, buyable, lowest total incl. known shipping), and that only sites serving the locale respond. That is substantive behavioural context for a search call, including the notable gotcha that results silently shrink to locale-serving sites.

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, front-loaded with the capability and the return payload, then the routing hint last. Every clause carries information an agent cannot get from the structured fields.

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?

Five parameters, one required, one enum, no output schema — the description compensates by describing the shape of the returned data and the locale-dependent narrowing of the result set. Nothing an agent needs to call this correctly is missing.

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 the baseline is 3 and the schema already documents query, sites, locale and max_price in detail. The description adds only the typo-correction behaviour on the query and the market-scoping consequence of locale; the max_price and sites semantics are restatements of 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?

"Search every site's catalogue at once for a product, brand or kind of product" gives a specific verb, resource and cross-site scope, and then states what comes back (site, page URL, list price, offer summary). That is enough to tell it apart from compare_prices, best_deals and find_by_code without opening a 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?

It explicitly routes the agent to a sibling: "Use compare_prices for the shops and their links," which defines the boundary in terms of what this tool does not return. It also implies default behaviour (every site, default locale nl-NL), but gives no guidance on when to prefer find_by_code or best_deals, nor when a search would be wasteful.

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