KBeauty Verified™ — K-beauty ingredient rules

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

With no annotations, the description carries the full burden and does substantial work: it discloses the attribution requirement, the non-commercial-use restriction, the data sources, and the explicit negative scope (no safety ratings/lab tests). It does not state that it is a read-only informational call with no side effects, but for a zero-param tool this is a rich disclosure.

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?

Content is front-loaded — the identity and scope come first, then the routing hint, source attribution, and legal caveats. It is somewhat long and clause-heavy, with the attribution rule appearing twice in near-identical form, but each remaining sentence carries real information for an agent.

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 parameterless, annotation-free, output-schema-free orientation tool, the description covers what the data is, where it comes from, what it must not be used for, and the legal obligations on the caller. An agent has everything needed to call it and use its answer 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?

The tool takes zero parameters, so per the baseline this scores 4. There is no parameter semantics to add, and the description correctly spends its budget on scope and licensing rather than inventing parameter detail.

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 concretely states what the tool returns: what KBeauty Verified is, its data provenance (MFDS, CosIng, FDA), its limitations (no safety ratings), and licensing/attribution rules. That is far more specific than a tautological 'about' restatement. It does not directly contrast itself with siblings like search_ingredients, though 'call this first if unsure' implies a routing role.

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?

Explicitly tells the agent when to call it ('Call this first if unsure'), which is clear usage context for a zero-parameter orientation tool. It also establishes a when-not boundary by stating the tool is not a safety rating, lab test, or medical advice that should be relied on for those questions. No explicit named alternative sibling, but the guidance is actionable.

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?

No annotations are provided, so the description carries the burden and does well: it discloses that answers come only from KBeauty Verified records with sources, that it reports official MFDS/CosIng/FDA positions, and explicitly disclaims that it is not a safety rating, lab test, or medical advice. It omits rate limits, latency, and behaviour when no record matches.

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 core purpose is front-loaded in the first sentence, followed by source, attribution requirement, and scope disclaimers. All content earns its place, though the attribution/linking instruction mid-paragraph interrupts the task-oriented flow slightly.

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 and no annotations, the description must stand alone, and it covers source, answer provenance, citation fields (url/cite), and scope limits. It is close to complete for a one-parameter tool, lacking only expected answer shape or multi-record/pagination behaviour.

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 0% and the single 'question' parameter is undocumented in the schema, so the description must compensate. It does specify the language (English) and the accepted topic scope (ingredients, products, sunscreen filters, recalls, Korea/EU/US cosmetic rules), which meaningfully constrains valid input.

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 (ask a question about K-beauty ingredients, products, sunscreen filters, recalls, or cosmetics rules) and scopes the answer domain to KBeauty Verified records. It differentiates by function from the lookup/search siblings, though it never explicitly contrasts itself with search_ingredients or lookup_ingredient.

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: open-ended English questions answered from official records, with the source explicit. But there is no guidance on when to prefer this over the sibling search/lookup tools, nor any refusal/fallback behaviour for questions outside the K-beauty scope.

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?

With no annotations, the description carries the full burden and does well: it discloses that the submitted list is not stored, identifies the underlying data sources (MFDS, CosIng, FDA), and states the attribution requirement plus the url/cite fields returned. It does not cover rate limits, error behavior, or input validation, so it is strong but not exhaustive.

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 core action and scope are front-loaded in the first sentence, which is the right priority. The 'not a safety rating' disclaimer is stated twice in slightly different words, which is redundant padding, and the attribution sentence is long.

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, but the description compensates by naming what each result contains (prohibition/limit/condition status per jurisdiction, plus url and cite links). Combined with the privacy and disclaimer context, an agent has enough to call it correctly; only error handling and response shape remain unspecified.

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 schema already documents both ingredients (comma-separated) and sunscreen (U.S. filter rules). The description adds only the framing that the list is 'as printed on a label' and never mentions the sunscreen flag, so it does not meaningfully exceed the schema 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?

The description states a concrete verb and resource ('Paste an ingredient list... get... which listed ingredients are prohibited or have limits or conditions') and scopes the output to three jurisdictions. It is clearly a list-level check, implicitly distinct from the single-ingredient siblings lookup_ingredient and search_ingredients, though it never names an alternative 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?

The opening clause tells the agent the input context ('as printed on a label'), and the closing caveats set boundaries ('not a safety rating, a lab test or medical advice'). It also states an obligation attached to use (attribute KBeauty Verified and link the per-result url/cite). It stops short of explicitly routing the agent away from sibling tools for single-ingredient lookups.

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?

With no annotations, the description carries the full behavioral burden and does so well: it names the data source (KBeauty Verified, MFDS/CosIng/FDA records), states attribution obligations, and explicitly disclaims that it is not a safety rating, lab test or medical advice. It also flags the real limitation that ingredient amounts are not shown, so limits cannot be verified. It stops short of describing the result shape or any access/rate constraints.

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 front-loads what is returned and keeps the caveat, attribution and disclaimer tight. Every sentence serves a purpose, though the attribution/disclaimer clauses make it longer than a minimal lookup definition.

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 one-parameter lookup with no output schema, the description conveys the substance of the return (ingredient list plus per-region prohibitions/limits/conditions) and its legal/interpretive caveats. It does not sketch the result's field structure, which is the main remaining gap given there is no output schema.

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?

There is a single parameter with 100% schema description coverage, so the schema already defines 'slug' adequately (including where to get it). The prose adds no further parameter meaning; 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 states a specific verb and resource — retrieving one K-beauty product with its full ingredient list and the Korea/EU/US regulatory status of each ingredient. It is clearly scoped as a single-product lookup, distinguishable in spirit from search_products, though it never names a sibling tool 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?

The description itself gives no when-to-use or when-not-to-use guidance versus siblings like lookup_ingredient, check_ingredient_list or search_products. The only routing hint is indirect, carried in the schema's slug description ('slug from a search result'), which implies a search-then-fetch workflow.

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?

With no annotations, the description carries the full burden and does so: it discloses the returned fields (status, maximum, conditions, required label warning, source URL, date checked), the data provenance (official MFDS/CosIng/FDA records), a citation obligation, and an explicit interpretation caveat that this is not a safety rating or medical advice. That is substantially more than the structured fields supply.

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?

Purpose is front-loaded and every later sentence carries operational weight (routing, attribution, disclaimer). The first sentence is a dense run-on list that packs four region/return items into one clause, which slightly taxes readability, but there is no filler.

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 and no annotations, the description must explain both what comes back and how to interpret it, and it does: per-region status/maximum/conditions/warning/URL plus functional-cosmetic amounts, along with the citation requirement and scope limits. Nothing an agent needs in order to call or report this tool 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 coverage is 100% for the single 'name' parameter, so the baseline would be 3. The description earns above baseline by expanding accepted identifier types to INCI, common, trade, Korean name, or slug, which is a meaningful widening of the schema's terse 'ingredient name or slug'.

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 opens with a specific verb+resource ('One cosmetic ingredient') and enumerates exactly what is returned: per-region rules (Korea MFDS, EU CosIng, U.S. FDA) plus Korea's functional-cosmetic listing. It explicitly distinguishes itself from the sibling search_ingredients, so an agent can route correctly without opening any 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 names a concrete alternative and the condition that selects it: 'Use search_ingredients first if the name is ambiguous.' That is a real routing rule, not an implication. It stops short of stating exclusions (e.g. when to prefer check_ingredient_list or get_product instead), so it is strong but not exhaustive.

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?

With no annotations, the description carries the behavioral load and does meaningful work: it discloses the data source, the attribution requirement, the underlying official registries (MFDS, CosIng, FDA), and an explicit limitation that this is not a safety rating or medical advice. It omits return structure and whether results are paginated beyond the 10-item cap.

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 front-loads what the tool returns, then the source, then the required attribution and the disclaimer. Every sentence serves a purpose, though the legal/disclaimer clauses are dense and could be tightened slightly without losing meaning.

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 feed with no annotations and no output schema, the description covers sourcing, attribution, and interpretation caveats well, and even names the `url`/`cite` fields present in results. It is slightly thin on the shape of returned records and on whether the feed is time-windowed or cumulative.

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 single `limit` parameter has 0% schema description coverage, so the description must compensate. 'Up to 10' adds marginal meaning but largely restates the schema's maximum/default of 10; it does not explain the parameter's effect or behavior when lowered.

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 specific content: rule changes, K-beauty recalls/alerts, and newly checked products, with a cap of 10. That distinguishes it from the lookup/search siblings, which target products and ingredients rather than a change feed. It stops short of an explicit 'use this instead of X' contrast, but the resource is unambiguous.

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?

There is no explicit when-to-use or when-not-to-use guidance, nor any named alternative among the siblings. Usage context is only implied by the content types it returns (a recency feed), and the attribution/disclaimer sentences are obligations rather than selection guidance.

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?

No annotations provided, so description carries full burden; it discloses data source (KBeauty Verified), required attribution with url/cite, and explicitly disclaims that it's not a safety rating or medical advice. Lacks detail on response shape/pagination but covers important behavioral traits.

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?

Front-loads purpose, but the citation/attribution and disclaimer clauses are long and consume much of the description. Information earns its place but structure mixes core function with legal boilerplate in one block.

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?

Given no annotations, no output schema, and 0% schema coverage, the description should explain return fields and the limit parameter. It covers source and disclaimers well but leaves result structure and the second parameter under-specified.

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 0%, so description must compensate; it clarifies 'q' as a word matched across four name types, which is useful, but never mentions the 'limit' parameter or its max of 10 (though it says 'up to 10'). Partial compensation only.

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?

Clear verb 'find' plus resource 'ingredients' and specifies the search targets (INCI, common, trade, Korean name), which distinguishes it from lookup_ingredient and check_ingredient_list.

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?

Implies usage by naming search fields and cap of 10, but never contrasts with sibling lookup_ingredient or explains when to prefer exact lookup vs this search. Usage is inferable but not directed.

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?

With no annotations, the description carries the full burden and does substantial work: it names the data source, mandates attribution and exact-URL linking, and explicitly disclaims that the data is not a safety rating, lab test, or medical advice. It omits pagination/return-shape detail, but the behavioral context is well beyond typical.

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 core purpose is front-loaded in the first clause, and the trailing attribution/disclaimer text is compliance-relevant rather than filler. It is slightly dense with boilerplate, but every sentence carries information an agent needs to use the data legally and correctly.

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 search tool with no annotations and no output schema, the description covers purpose, source, data nature, attribution duties, and limitations. The only real gap is the shape of results beyond the mentioned url/cite fields, which is minor for a discovery 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 0%, so the description must compensate, and it does: 'a word in the product or brand name' maps to q, 'optionally within one brand' maps to brand, and '(up to 10)' conveys the limit cap. Semantics are conveyed even though exact parameter names are not tied to descriptions.

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 specific verb and resource ('Find K-beauty products'), names the search scope (a word in the product or brand name), and clarifies the optional brand restriction and result cap. It does not explicitly differentiate from siblings like get_product or search_ingredients, so it falls short of a 5, but the purpose is unambiguous.

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 explains what the tool returns and how to cite it, but gives no guidance on when to use it instead of the alternatives (get_product for a known item, search_ingredients for ingredients). 'Optionally within one brand' hints at narrowing, but there are no exclusions or alternative routing.

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