株式会社コンテンシャル

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 one useful behavioral trait — that the complete body text is returned (not a snippet) — but discloses nothing about pagination, size limits, or failure modes.

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 front-loaded sentences: first what it does, then when to use it. No filler or repetition, though the enumeration of content types is slightly 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?

An output schema exists so return format needn't be explained, annotations cover safety, and the parameter is fully described in the schema. The only omission is any hint of how this differs from the sibling get_page.

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 single 'id' parameter (page URL/path, Japanese acceptable) is already fully documented in the schema. The description adds no syntax or format guidance beyond it, 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?

States a specific verb and resource: it returns the full body of a page on the Contential site 'from beginning to end'. It differentiates itself from search (the discovery tool that surfaces the page) but says nothing about the near-identical sibling get_page, leaving that distinction for the agent to infer.

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 clear usage context: use it to read in detail content found via search — service descriptions, case studies, news, SEO Note!! articles, monthly reports. No explicit when-not condition or named alternative for the read step, but the trigger is unambiguous.

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 valuable non-obvious context: this is a deprecated legacy alias kept only for backwards compatibility. It does not detail the differing return format, which is the one remaining behavioral 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?

Three short sentences, front-loading the legacy/deprecation status before the functional comparison with fetch. Efficient and appropriately sized, with no notable waste.

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, and the description says the returned format differs from fetch without describing it, which is a small gap. However, since the tool is deprecated and the description routes new callers to fetch, the essential information an agent needs is present.

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 'url' parameter, so the schema already documents that a URL or path (Japanese allowed) is accepted. The description adds nothing beyond this, so the baseline of 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 concrete verb+resource (returns the page body) and explicitly distinguishes itself from the sibling 'fetch' by noting the response shape differs. It is clear what the tool does, though it never specifies how the format differs, which leaves the distinction slightly abstract.

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 states exactly when to use it (legacy compatibility for users already connected) and gives an explicit alternative with a directive: use 'fetch' for new usage. Both the when and the when-not are present.

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 usefully adds the return content (titles and URLs), but says nothing about pagination, which matters for a list tool.

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 return value are front-loaded, which is good. The path-by-path enumeration is informative but long and bulky for a listing tool; it earns partial keep but weighs down the 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 simple annotated list tool with no output schema, the description covers what is returned and roughly what exists. The missing piece is pagination behavior given the limit/offset params, leaving a real gap for an agent paging through results.

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 the two parameters (limit, offset), and the description never mentions pagination at all. The description does not compensate for the schema's silence on how to page through results.

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: returns a list of pages with titles and URLs from a named site, and it explains the path taxonomy that organizes them. It is clear and distinct from a search, but it does not name or contrast against siblings like search_pages or site_overview.

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?

Offers a conditional use case ("use when you want to list case studies and news together"), which is clear context. However, it names no exclusions or alternatives, and the recommended scope is narrower than what the tool actually returns (all pages), which could mislead.

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 safety and scope are covered structurally. The description adds that results come with excerpts (抜粋つき) and that coverage is confined to one company's site, which is useful, but it says nothing about result limits, ranking, or pagination 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?

Front-loaded with the core action and scope, then the coverage list, then the when-to-use rule and query style. The content-type enumeration is somewhat long but each item tells the agent what can be retrieved, so it earns its 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 detail is not required, and the description covers domain scope, invocation trigger, and query phrasing. The one meaningful gap is the absence of any differentiation from the sibling 'search_pages', which an agent would need to route 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% and the single 'query' parameter is already documented with an example ('料金 支払い方法'). The description reinforces the short-keyword style with additional examples, adding only marginal meaning beyond the schema, so the baseline 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?

States a specific verb+resource: searches the official site of a named company and returns matching passages with excerpts, and enumerates the content types covered (services, case studies, notices, SEO Note!! articles). It is clear what the tool does, but it never distinguishes itself from the sibling 'search_pages', which sounds functionally identical, so an agent cannot confidently choose between 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?

Explicit routing instruction: 'この会社やサービスについて質問されたら、まずこれを使ってください' tells the agent exactly when to reach for this tool, and it gives query-construction guidance ('「特許」「2026年8月 レポート」のように短い言葉で探します'). It lacks any when-not or alternative-tool guidance, notably against search_pages and site_overview.

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 it as a safe read-only operation with `readOnlyHint=true`, `openWorldHint=false`, and `destructiveHint=false`. The description adds important historical context: it is a legacy alias and returns a different shape than `search`, which helps an agent set expectations, though it does not describe pagination or output 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?

Three short sentences, front-loaded with the legacy status and ending with the routing instruction. Every sentence serves a purpose with no wasted text.

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 two-parameter legacy tool with annotations and no output schema, the description provides enough to avoid misuse by routing users to `search`. It could say more about the differing return shape, but the essential deprecation and alternative are covered.

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 description does not mention the `query` or `limit` parameters at all. Schema coverage is only 50% (query is described, limit is not), so the description should compensate but instead adds no parameter meaning beyond 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?

The description states this is a legacy search function under the former name, that it searches within the site like `search`, and that its return shape differs. This gives a clear verb+resource and explicitly distinguishes it from the sibling `search` tool.

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 says the tool is kept for users already connected and that new callers should use `search` instead. This is direct when-to-use and when-not-to-use guidance with a named alternative.

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 fully covered externally. The description adds nothing behavioral beyond that (no output format, caching, or freshness details), which is acceptable but not additive for a read-only tool.

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 sentences with the purpose front-loaded, then supporting description of the company/overview content, then the usage trigger. The middle company-profile sentence is slightly promotional but does inform what the overview contains, so it mostly 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 zero-parameter, read-only summary tool with no output schema, the description conveys what the agent gets back (company overview) and when to call it, and annotations cover safety. Complete enough that nothing needed to invoke it 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?

The tool takes zero parameters, so the schema carries no semantic burden and the baseline for a no-param tool is 4. Nothing in the description could mislead about inputs since there are none.

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 (returns the overview) and a concrete resource (the official site of Contentual Inc.), so the agent knows this is a site-level summary rather than a page fetch. It does not explicitly differentiate itself from generic siblings like get_page or fetch, staying at the 'clear but undifferentiated' level.

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 a usable when-to-use condition: 'use when you first want to know what kind of company it is and what you can request,' which implies this should be an early/orientation call. No alternatives are named and no exclusions are given, so it falls short of the explicit when/when-not/alternative guidance a 5 would require.

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