【公式】アイレディース化粧品 - アイスター商事

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context: it returns the full body text and the corpus retains past-year pages, so results may include outdated or discontinued content. It does not describe pagination or truncation behavior for long pages.

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 the follow-on sentences are all relevant to correct invocation. It is somewhat long and several sentences read as answer-behavior policy rather than tool semantics, which slightly dilutes focus but does not waste space.

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 an output schema present, return-value explanation is unnecessary, and the single parameter plus rich usage rules fully equip an agent to call it correctly. Nothing essential 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% and the single `id` parameter is already documented in the schema. The description restates it (search result id = page URL, or URL/path) with 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?

State a specific verb+resource: it returns the full body text of an already-loaded page on ai-star.co.jp, and explicitly contrasts full text with search's excerpts. However, it does not distinguish itself from the sibling get_page, leaving ambiguity about which of the two to pick for a single page read.

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?

Explicit about when to use it (accuracy-critical facts: prices, shipping, application periods, ingredients, allergens, company info) and when not to rely on excerpts from search. It also adds domain rules for handling past-year pages, sold-out/discontinued markers, and cosmetic/beverage claims, which is far beyond typical 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful context beyond them: this is a deprecated/legacy alias, and its return shape differs from fetch. It stops short of saying how the shape differs, which matters since there is no output schema.

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 key information (legacy alias, use fetch instead) is present, but the leading sentence embeds an unexplained site title and domain that reads like scraped noise rather than tool metadata. That muddies the front-loading of an otherwise short description.

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 deprecated one-parameter alias with no output schema, the description tells the agent what it does, that it is legacy, and to prefer fetch. The only gap is that it never characterizes the differing return shape it advertises.

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 the single url parameter is fully documented in the schema, so the description adds no further parameter meaning. Baseline 3 is appropriate when the schema carries the load.

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 resource (the page body) and explicitly frames this as the legacy name of the fetch functionality, naming the sibling it overlaps with. An agent can distinguish it from fetch without opening either 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 gives an explicit directive: use fetch when using it newly, and notes this one is retained only for existing users. The when-not-to-use condition and the alternative are both stated directly.

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 establish read-only, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real behavioral value beyond that: pagination mechanics (50 per page, limit 200, offset continuation) and the caveat that multiple year-variants of the same product may appear, with guidance to pick the latest. It does not state ordering/sort behavior, which is the remaining gap.

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-loaded with purpose, then pagination, then usage context. Dense but every clause carries information (paths, pagination, year-selection caveat); the long enumeration of section paths makes it heavier than strictly necessary.

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 names the returned fields (title and URL), covers pagination, and warns about duplicate year variants. Combined with the annotations, an agent has enough to call this correctly, with only sort order 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 coverage is 0%, so the description must carry parameter meaning, and it does: it explains the 50-item default page size, the 200 maximum for limit, and that offset retrieves the continuation. That compensates well for undocumented schema properties, though it does not explicitly tie names to each parameter.

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 and resource ('ai-star.co.jpの読み込み済みページの一覧を、タイトルとURLで返します') and names exactly what is returned. It also separates itself from the search siblings by framing itself as the fallback when searching fails.

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?

Gives an explicit trigger condition ('searchで見つからないとき') plus a positive use case (surveying what pages exist), and enumerates concrete section paths to look under. The alternative tool (search) is named rather than left to inference.

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/openWorld=false/no destructive behavior, so the safety profile is covered; the description adds the crucial behavioral boundary that only pre-loaded pages are searched (not the live web, not post-load updates) plus the 'don't fill gaps by guessing' rule. That is real context beyond the structured fields.

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 and scope are front-loaded, and despite being a multi-sentence paragraph every sentence adds either routing or behavioral value. It is slightly long, with the rephrase/fallback instructions bordering on over-explanation.

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 an output schema present, return-value explanation is not needed, and the description still covers scope boundaries, trigger scenarios, and failure handling. Nothing an agent needs to use it correctly appears to be 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% for the single 'query' parameter, so the baseline is 3. The description earns extra credit by supplying concrete rewriting mappings (e.g., おせち→なごやかセット白鳥, 日焼け止め→白光) that materially improve how the query should be phrased.

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 (excerpts with URLs from the loaded pages of ai-star.co.jp) and names the covered domains/products precisely. It does not, however, differentiate itself from the similar-looking sibling 'search_pages', leaving an agent to infer which site-search tool to pick.

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 says to use this before answering from the model's own knowledge, specifies the topics that trigger it (company products, seasonal items, FAQ, recruitment), and gives a concrete when-not and fallback path: rephrase (with synonym examples), then read candidate pages, and never guess. This is precise routing 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?

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds genuinely useful non-annotation context: this is a deprecated/legacy alias kept for backward compatibility, and its return format differs from `search`. It does not detail the actual return shape, pagination, or result cap, which keeps it short of a 5.

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-loaded with the legacy/deprecation status, then the behavioral difference, then the routing advice — a sensible order. It is slightly padded by the long quoted site name, but every sentence 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?

For a two-parameter, deprecated read tool with no output schema, the description supplies what an agent most needs: it is legacy, prefer `search`, and the return format differs. The omission of any detail on that differing return format is the main residual gap.

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 only 50% (query is documented in-schema, `limit` is not), and the description adds no parameter information at all — it never explains the result cap, default of 5, or what `limit` controls. With low coverage the description is expected to compensate, and it does not.

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 action — it searches within the site (サイトの中を探す) — and explicitly frames itself as a legacy alias of the sibling tool `search` that returns a different shape. An agent can distinguish it from `search` without opening the schema, though the 'former name of the function' framing is slightly indirect about what the tool itself does.

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 gives an explicit when-to-use (retained only for users already connected to it) and a clear alternative ('新しく使うときは search を使ってください' — use `search` when starting fresh). This is a textbook routing instruction with the alternative named and the selection condition 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 establish readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context: warning not to conflate Ai-star group companies, to answer sales-method questions strictly from the site's own compliance statements, and to escalate individual order/skin/health inquiries to the contact form rather than guessing.

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 first sentence front-loads the return contents well, which is good structure. However, a substantial portion of the text concerns domain answering policy (company-name confusion, visiting-sales compliance, escalation) rather than the tool's own mechanics, making it longer than a tool definition needs to be.

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 input parameters and no output schema, the description carries the burden of explaining the return payload and does so by enumerating the overview fields. It also supplies the missing escalation target URL, leaving little an agent needs that is absent.

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 rubric the baseline is 4. The description correctly implies a parameterless, whole-site call and adds no conflicting parameter expectations.

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: it returns an overview of ai-star.co.jp (type, description text, number of pages loaded, main pages). The scope is precise enough to distinguish it from fetch/get_page/list_pages, 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?

'最初にサイトの全体像をつかみたいときに使います' gives a clear triggering condition. It does not, however, say when NOT to use it or point to a specific alternative (search_pages, list_pages) for narrower needs, so there is no explicit routing.

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