Coupondroid España

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description earns credit for genuinely non-obvious behavior: coupons are 'live' only, ordered best-first, and 'each coupon url reveals the code on the site' — telling the agent the discount code is not inline in the payload. It does not describe pagination or truncation behavior.

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 dense sentences, zero filler, and the core identity ('One shop by slug') is front-loaded before the payload enumerations and the code-reveal caveat. Every clause carries information.

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 must carry the return-value burden, and it does: it names coupons/offers, ordering, categories, and country variants. The minor gap is that it never clarifies what `limit` restricts, leaving the only tunable parameter's effect ambiguous.

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% and both parameters carry their own descriptions (slug sourcing, limit default 30 with a 50 cap), so the schema does the heavy lifting. The description reinforces the slug key but adds nothing about what `limit` bounds (coupons vs categories), 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?

It names the specific verb+resource ('One shop by slug') and enumerates the payload: live coupons and offers, categories, and the same shop on other countries' sites. This clearly separates it from list_coupons (aggregate feed) and search_shops (discovery), so an agent can pick it 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?

Usage is implied: a single-shop lookup keyed by a slug obtained from search_shops. However, the description never states when to prefer this over list_coupons or when the cross-country/category data matters, and gives no exclusions or prerequisites. Implied but not explicit.

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 readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered without the description. The description's one added behavioral fact is that results include each category's site page, which is mild context; it says nothing about ordering, count, or caching.

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 short sentences: the first defines the resource with examples, the second explains the payoff. Nothing is wasted and the resource definition is front-loaded.

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 parameters and no output schema, the description must characterize the return value, and 'with their page on the site' plus the examples does so adequately. Only minor gaps remain (pagination, ordering, whether the list is exhaustive) and the annotations cover the safety dimension.

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?

The tool takes zero parameters, so per the baseline the schema carries the entire burden and the description cannot add parameter meaning. It does mention a `slug` field, but that is a returned value consumed by other tools, not an input, so the baseline 4 stands.

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?

Names a specific resource (shop categories of this site) and grounds it with concrete examples (fashion, electronics, travel), plus the useful detail that each comes with its page on the site. It is distinguishable from siblings because it positions itself as the slug source for search_shops/list_coupons, though the verb itself is only implied by the tool name.

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 offers downstream usage ('Use a `slug` to filter `search_shops` or `list_coupons`'), which tells the agent why the output matters, but never states when to call this tool versus siblings like site_info or get_shop, and gives no exclusions or preconditions. Usage is implied rather than specified.

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 cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds real behavioral context beyond that: results are sorted by 'featured' by default, and critically that the coupon code is not returned directly but is revealed via the coupon `url` on the site.

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 with no filler. Scope is front-loaded, sort behavior follows, and the code-revelation caveat is the last and most actionable detail. Every sentence earns its place.

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 list tool with full schema coverage and no output schema, the description covers the essentials, including the non-obvious fact that codes come from the URL rather than the payload. Pagination (limit/offset) is left entirely to the schema, which is acceptable at 100% coverage.

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 largely restates what the schema documents (shop, category, type, sort) and adds only marginal nuance, notably that 'featured' means 'exclusive and top first' — useful but not enough to exceed 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?

States a specific verb+resource ('Live coupons and offers on this site') with scope ('across shops or filtered by shop, category or kind'). The sibling set (get_shop, list_categories, list_events, search_shops, site_info) is clearly distinct in domain, so no explicit sibling routing is needed, but the description also does not name one.

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 implies usage by describing the filtering and sorting modes ('filtered by shop, category or kind', sort options), but never says when to prefer this over a sibling like search_shops or list_categories, nor any when-not condition. Usage is inferable rather than stated.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and side-effect profile is fully covered structurally. The description adds only content scope (what events exist and that dates/pages are returned); it says nothing about ordering, freshness, or whether past events are excluded.

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 front-loaded sentence that leads with the resource and scope before the parenthetical examples. The example list is slightly long but each example earns its place by anchoring what counts as an 'event'.

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 return-value burden and does deliver it ('with their dates and page'). Combined with annotations covering safety and the closed-world scope, this is nearly complete for a simple no-arg list tool; only result ordering/freshness is 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?

The tool takes zero parameters, so the schema needs no supplementation and the baseline is 4. The description correctly avoids inventing parameter semantics for a no-arg call.

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 the resource precisely (current and upcoming sales events and campaign pages on this site) and grounds it with concrete examples (Black Friday, CyberDay, Hot Sale, seasonal pages). It is clearly distinct from siblings like list_coupons or list_categories by resource, though it never explicitly contrasts 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?

Usage is implied by the scope words 'current and upcoming' and 'on this site', which tell the agent what subset this tool covers. However, there is no explicit when-to-use, when-not-to-use, or pointer to an alternative (e.g., list_coupons or site_info) for related 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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results are limited to shops with live offers and include a per-shop offer count, and the default ordering is most-offers-first.

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 tight sentences with no filler; the resource definition and scope come first, then the default-ordering behavior. Every clause carries information.

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 usefully summarizes the return shape (shops with offer counts), and annotations cover the safety profile. It is slightly thin on pagination/limit behavior, but that is addressed in the schema, so an agent has what it needs to call it correctly.

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 three parameters are documented in the schema (including the default limit of 20 and the category-slug reference to list_categories). The description adds only the combined name/category semantics and default sort, so the 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?

States a specific verb (search) and resource (shops/merchants) plus the scoping constraint that only shops with live coupons/offers are returned. It also names the filter dimensions (name and/or category) and the payload (live offer counts), which cleanly separates it from the single-shop lookup get_shop.

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 implies when it is useful (finding shops by name/category) and explains the no-filter default ordering, but it never names get_shop as the alternative for a known shop or states exclusions. Usage is inferable rather than explicit.

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 readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the payload (counts, main pages, sister sites), which matters since there is no output schema. It stops short of format/volume details.

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 sentence, front-loaded with the resource identity, then a terse action directive ("Call it first"). No filler and every clause contributes return-value information.

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 parameters, no output schema and full annotation coverage, the description's main job is to describe what comes back, which it does thoroughly. Minor gaps remain (structure of "main pages" and "sister sites", any caching/pagination), but these are low-stakes for a zero-arg metadata 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?

The tool takes no parameters, so the baseline is 4. Nothing in the description needs to compensate for a schema gap, and there are no parameter semantics to clarify.

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 enumerates precisely what the tool returns about the site itself (name, country, language, currency, shop and live-offer counts, main pages, sister sites), which is a clearly distinct resource from every sibling (get_shop, list_categories, list_coupons, list_events, search_shops), all of which deal with shops/coupons rather than site metadata.

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?

"Call it first" is an explicit, unambiguous usage directive that tells the agent when to reach for this tool. It does not name alternatives or state exclusions, but the sequencing guidance is concrete rather than implied.

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