Wherbi

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: the drop is computed against the shop's own 30-day low and never against a shop's advertised "was" price, and results carry site, product page and shop link. It stops short of describing result ordering guarantees or volume beyond the schema's limit.

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 sentence with zero filler, front-loaded on the headline result before the metric definition and included fields. Every clause earns its place, including the parenthetical ruling out advertised "was" prices.

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 three-parameter, no-output-schema read tool this is close to complete: it defines the ranking basis, the market scoping, and the shape of each result (site, product page, shop link). Only the ordering/pagination behavior and default locale handling in the answer are left implicit, and the schema covers the defaults.

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; the description modestly adds meaning by framing locale as a market that determines shops, prices and currency, and by scoping results to "the locale's market". Sites and limit semantics are left entirely to the schema, which already handles them well.

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 names a specific resarah of result (largest real price drops right now, per locale market, across sites) and defines the drop metric precisely as a shop's current price against its own lowest price of the preceding 30 days. That methodology distinguishes it from compare_prices or search_products, though the siblings are never named explicitly.

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 implied — this is a browse/discovery tool for aggregate price drops, not a lookup for a specific product — but the description never states when to prefer it over compare_prices or search_products, nor any exclusions. The reader must infer the routing from the metric definition.

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

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

Annotations already declare readOnly, idempotent, non-destructive and non-open-world, so the safety profile is covered. The description adds genuinely new behavior: result ordering (cheapest total first, out of stock last), the fields returned (price, shipping, stock, check time, shop link), and that each row is augmented with that version's best price in the site's other markets.

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 a single front-loaded sentence that opens with the core action and pushes output detail into a parenthetical. The sentence is dense and slightly run-on with its trailing cross-market clause, but no wording is redundant.

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 carries the burden of describing results and does so (ordering, field list, cross-market best price). Combined with the fully documented four-parameter schema, 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 coverage is 100%, so all four parameters are already documented, including the locale enum and the URL-or-id-plus-site pattern. The description reinforces the site/locale coupling ('the locale's market on the site that lists it') but adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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 names a specific verb and resource ('Shop prices of one product version side by side') and scopes it to a locale market and the site that lists it, which separates it from search_products (finding products) and best_deals (aggregate deals). It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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 implied by the phrasing 'on the site that lists it' and by the cross-market extension, but there is no explicit when-to-use/when-not statement and no routing to search_products or list_sites for obtaining the site key or product id. The agent must infer the workflow from the schema descriptions rather than the description text.

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

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuine value beyond that: results are per-site, offers are ordered by cheapest total, each carries a link, and the best overall price is surfaced, plus the market scoping rule that only sites serving the locale respond.

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?

Three tight sentences: identifier scope first, return shape second, no-match semantics last. The closing "never a guess" line earns its place by preventing pointless retries, though the phrasing is slightly promotional rather than purely informative.

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 only three parameters, full schema coverage and no output schema, the description carries the return-value burden well by describing per-site matches, offer ordering and the best price. Only the miss case's return shape (empty vs. per-site omissions) is left unstated.

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%, with the code formats, the sites default and the full locale enum already documented in the schema. The description reinforces the locale-market semantics and the "every site" default but adds no syntax or constraints the schema lacks, so it sits at the baseline.

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?

"Exact identity lookup" names a specific verb and scope, and enumerates the three accepted identifier types (GTIN/EAN, manufacturer item number, LEGO set number), which is enough to separate it from a fuzzy catalogue lookup. It never names the sibling it is not (search_products), so differentiation is inferred from the word "exact" rather than stated.

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 framing "exact identity lookup" plus "Never a guess: no match means no site lists that exact product" tells the agent this is the tool for a known code and that a miss is terminal, implicitly steering keyword queries elsewhere. It stops short of explicitly naming search_products as the alternative for partial or descriptive queries.

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

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context by explaining that these are independent price-comparison sites and that each has its own MCP server for deeper category, brand, guide, and toplist questions.

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 description is a single front-loaded sentence that immediately states what the tool returns. The long parenthetical category list is informative but slightly dense; overall it remains efficient with no redundant sentences.

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 simple one-parameter list tool with rich annotations and no output schema, the description adequately covers the returned site fields and the role of each site's MCP server. It could be more complete by explicitly routing usage against sibling tools, but it is sufficient for correct invocation.

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%, and the single locale parameter is fully documented with enum values and market/language semantics. The description adds no additional meaning about locale filtering, so the schema does the heavy lifting and the baseline of 3 is appropriate.

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 clearly identifies the resource as the independent price-comparison sites searched by the server and enumerates the returned fields (key, name, coverage, markets, languages, home page, MCP server). It is distinct from the product-search siblings, though it does not explicitly contrast itself with them.

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 implies the tool is for discovering available sites and notes that each site has its own MCP server for deeper questions. However, it does not state when to call list_sites instead of search_products, compare_prices, best_deals, or find_by_code, nor does it say to use it before locale-specific searches.

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

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.