Pono-Pono｜フェムケア・デリケートゾーンケア情報

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds nothing behavioral beyond that: no statement about failure modes for bad/unknown IDs, URL-vs-path handling, caching, or whether the page body is returned whole. The fidelity instructions describe desired answer behavior, not tool 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?

The purpose is front-loaded, but the remaining ~80% is a block of answer-writing directives (don't mix product descriptions with general info, don't assert what the page doesn't say) that do not help an agent select or invoke the tool. For a one-parameter read tool this is bloated and off-purpose.

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?

Return values are covered by an existing output schema and the single parameter is fully documented, so the definition is complete for invoking the tool. Its remaining weakness — failing to separate this tool from get_page — is a selection issue rather than a missing invocation detail.

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 required parameter with 100% schema description coverage; the schema already explains that id is the page URL or path and that Japanese is acceptable. The description adds no additional syntax or format meaning beyond that, 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?

The opening clause states a specific verb and resource — reading the body of a specified page — which is unambiguous on its own. However, it never distinguishes itself from the near-identical sibling get_page (or search_pages/site_overview), leaving an agent unable to tell which read tool to pick. Clear purpose, but zero sibling differentiation.

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 bulk of the text tells the agent how to phrase its answer (cite the URL, don't speculate, prioritize original wording), not when to invoke this tool versus get_page, search, or site_overview. There is no when-to-use, no when-not-to-use, and no named alternative. Selection guidance is effectively absent.

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 usefully adds deprecation status and that the return shape differs from fetch, but it never says how the shape differs, nor anything about errors, limits, or truncation of page bodies.

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 short sentences that each carry a distinct load: identity/legacy status, behavior relative to fetch, and migration instruction. The legacy notice is front-loaded. Minor redundancy in naming the site and repeating the backwards-compatibility rationale.

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 single-parameter, read-only legacy alias with no output schema, the description supplies everything needed to decide whether to call it: what it does, that it is superseded, and the preferred alternative. The only omission is the nature of the differing return format, which is low-stakes given the agent is told to use fetch instead.

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 there is a single 'url' parameter already documented in the schema ('ページの URL かパス（日本語のままでも可）'). The description adds no additional semantics about the parameter, 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 and resource ('fetch と同じようにページの本文を返します') and explicitly identifies itself as the former name of the fetch tool, so an agent can place it against its sibling immediately. It is slightly indirect because it defines itself by reference to another tool rather than describing its own output, but the core purpose (read page body) is unmistakable.

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 both sides of the routing decision: this exists only for already-connected clients ('すでにつないでいる人のために残しています'), and new usage should go to fetch ('新しく使うときは fetch を使ってください'). The alternative is named and the condition selecting it is 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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context: it returns titles and URLs only, and it explicitly warns not to infer body content from titles/URLs. It says nothing about pagination behavior despite the limit/offset parameters, so it is helpful but incomplete.

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 in the first sentence, which is good structure. The middle sentence listing content categories is long and enumerative, padding the definition, and the pagination parameters go unmentioned while category examples take up 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?

There is no output schema, so the description rightly explains that it returns titles and URLs. But for a paged listing tool with limit/offset parameters, the absence of any pagination guidance is a real completeness gap, and no alternative tool is offered for related needs.

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% for two parameters (limit, offset), so the schema provides no semantic help and the description carries the full burden. The description never mentions pagination, limits, or offsets, leaving an agent unable to know that results are paged or how to page through them.

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: it enumerates the titles and URLs of pages published on the Pono-Pono site and its purpose of grasping overall site structure. It further enumerates the content categories those pages fall into (product intro, FAQ/guide, brand concept, company overview, news, Journal), which sharpens what 'pages' means here. It does not explicitly distinguish itself from siblings like site_overview or search_pages, so it stops short of a 5.

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 implied usage: use it to understand the site's structure and to pick the page best matching a question, checking related pages as needed. However, no alternative tool is named (e.g., when to prefer search_pages or get_page), and there are no explicit when-not-to-use conditions. Usage is inferable but not spelled out.

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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds meaningful behavioral context beyond that: it is a closed site-internal search whose results are grounded in page text and URLs, and it explicitly warns against supplementing with information not present 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?

Purpose is front-loaded in the first sentence, followed by scope enumeration and answer-grounding instructions. The long topic list is somewhat dense but each item usefully delimits searchable scope, so little is pure 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 an output schema present, return values need no explanation, and annotations cover the safety profile. The description supplies scope, grounding expectations, and anti-hallucination guidance, leaving only the sibling-disambiguation gap ('search_pages') as an incompleteness for this low-complexity, single-parameter 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 coverage is 100% and the single 'query' parameter already carries its own example (料金 支払い方法), so the schema does the heavy lifting. The description lists topics to search but adds no syntax, format, or matching semantics beyond what the schema provides, which is the baseline 3.

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 (検索する) and resource (Pono-Pono公式サイト内) and even enumerates the content domains in scope, so the agent knows exactly what is searched. However, it never differentiates itself from the near-identical sibling 'search_pages', leaving ambiguity about which 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?

It gives rich context on what to look for and how to select results (prioritize pages matching the question, verify grounding text and URL, separate product info from general explanation, avoid speculation). But this is guidance for interpreting results, not for choosing this tool over 'search_pages', 'fetch', or 'get_page', so usage routing remains implied.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-structured context: the tool is deprecated and retained only for backward compatibility, and it diverges from `search` in return format. It stops short of saying how the format differs or noting pagination/limit 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 tight sentences plus a parenthetical; the deprecation notice is front-loaded and the redirect to `search` lands last, which is the right ordering. The parenthetical about the site name is slightly more context than strictly needed but earns its place by identifying the resource.

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, so the description carries some return-value burden; it flags that the shape differs from `search` but never describes it. For a low-complexity legacy alias whose main decision (avoid unless already integrated) is fully answered, this is adequate but not complete.

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?

With only 50% schema description coverage, the `limit` parameter (default 5, max 20) is documented nowhere, and the description says nothing about parameters at all — no syntax, no effect of `limit`, no query-format hints. The description fails to compensate for the coverage gap.

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 (site-wide search) and explicitly frames itself as the legacy name of the site-search function, naming the sibling `search` as the equivalent. It distinguishes itself from that sibling by noting a different return shape, though it defines its own behavior only relationally to `search` rather than describing the output itself.

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 (only for integrations already wired to it) and an explicit when-not-to-use with the named alternative: '新しく使うときは search を使ってください' (use search for new work). The agent has no inference left to make about tool selection.

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, destructiveHint=false, so the safety profile is covered. The description adds real behavioral value by instructing the agent to ground answers in official-site content and avoid claims beyond what the site supports, but it says nothing about what the call actually returns or its shape.

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 content is a single dense paragraph that is not front-loaded with the tool's function; brand-name etymology and product marketing consume space that a tool description should spend on purpose and routing. Sentences are grammatical but not all earn their place as tool documentation.

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 annotations covering the safety profile, the description supplies the domain context the tool presumably returns and adds answer-grounding rules, so it is reasonably complete for a simple overview tool. It is only thin on how this tool relates to its siblings.

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 there is no parameter semantics to convey; the baseline of 4 applies. The description does not need to (and does not) document inputs.

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 title (サイトの概要を知る) and the embedded content imply this tool surfaces a site/brand overview, but the description never states in tool terms what calling it does — it reads as the overview content itself rather than a statement of function. An agent can infer the purpose from the brand text, but no verb+resource framing is given and siblings are not distinguished.

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 guidance on when to call site_overview versus the siblings (fetch, get_page, list_pages, search, search_pages). The only procedural instruction concerns how to answer user questions (ground in official-site content, separate fact from general knowledge), not tool selection.

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