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

Without annotations, the description carries the full burden. It discloses the core behavior (combining site: filters and period phrases) and intended consumption, but does not describe the output format beyond 'query group' or explain how categories/includePeriodPhrases alter results. It omits details like whether output is a list or string, which leaves some behavioral transparency gaps.

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 is two sentences, front-loaded with the main action and resource, and contains no redundant filler. Every sentence earns its place: purpose, advantage, and direct usage instruction.

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 the tool's simplicity (3 params, no output schema) and strong schema coverage, the description covers the essential context: what it does, why it helps, and how to use the result. Minor gaps like exact return structure or category effects are acceptable because the schema explains them. It is complete enough for an agent to select and invoke 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 the schema documents all parameters. The description adds general context (e.g., site: filtering links to categories, 90s phrases to includePeriodPhrases) but does not add concrete syntax or format details beyond what the schema already provides. This meets the baseline but does not exceed it.

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 clearly states the tool 'generates' search queries (検索語を生成する) for current search engines, combining site: host filters with 90s-specific phrases. It explicitly frames the output as input for WebSearch, distinguishing it from sibling tools that perform retrieval or archival. The verb and resource are specific and 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 provides explicit context by stating the generated queries should be passed directly to the WebSearch tool and claims a higher hit rate than raw keywords. It implies when to use (for retro-site searches) but does not name alternative tools or give explicit 'when not to use' guidance, so it stops short of a 5.

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. It discloses that the tool collects across pages and aggregates by user site, and that it is the main tool for finding sites not in search engines. It does not mention rate limits or return format, but the aggregation behavior and comparison to CDX search provide substantive behavioral context.

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 is four sentences, each earning its place: it states the core function, gives examples, compares to a sibling tool, and states its strategic importance. It is dense, front-loaded, and free of 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?

Despite having no output schema, the description adequately explains what the tool returns (a site-level list) and provides example usage. It covers the main context (Geocities areas, 90s personal pages) and differentiates from sibling tools. A minor gap is that it does not describe the structure of the returned list, but overall it is context-rich.

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 input schema has 100% description coverage, so the baseline is 3. The description reinforces how the url prefix is interpreted and that results are grouped by site, but it does not add new per-parameter meaning beyond what the schema already provides. It earns a solid baseline score without exceeding it.

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 uses a specific verb '列挙する' (enumerate) and clearly specifies the resource: personal sites under a host/area. It explicitly contrasts with wayback_cdx_search (file-level vs site-level), making the tool's unique purpose 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?

It explicitly states when to use this tool: for discovering unknown 90s personal sites by specifying a host or area. It names the alternative (wayback_cdx_search) and explains why that alternative is less suitable (file-level results get buried). This is clear, actionable 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?

With no annotations, the description carries the transparency burden. It states '返す' (returns), implying a read-only operation, but does not explicitly mention side effects, authentication, or whether it performs network calls. For a simple lookup tool, this is adequate but not rich.

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 is two sentences with zero waste. It front-loads the core purpose, gives concrete examples, and then states use cases. Every clause 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?

Given one optional enum parameter, no output schema, and no annotations, the description is sufficiently complete. It explains what the tool returns and how to use it. No critical gaps remain for an agent to select and invoke 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 coverage is 100%, so the baseline is 3. The description does not mention the 'category' parameter at all, but the schema's own description already explains it well ('種別で絞る。community は発見の入口'). Description adds no extra parameter-level meaning.

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+resource: '一覧を返す' (returns a list) of legacy hosting services. It provides concrete examples (Geocities, @nifty, BIGLOBE) that distinguish it from sibling search/wayback tools, making its purpose immediately clear.

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 gives explicit use cases: 'CDX 探索の起点選びや site: 絞り込みに使う' (used for choosing starting points for CDX exploration and site: filtering). This provides clear context but does not explicitly mention alternatives or when not to use it, so it stops short of a 5.

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 of behavioral disclosure. It transparently reveals that Marginalia is English-only, Japanese queries fail, the service is mid-migration with unstable HTML, and automated fetching should be avoided. This is rich, candid context beyond minimal expectations.

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 is well-structured, front-loading the core purpose in the first sentence, followed by clearly marked constraints. Every sentence earns its place, providing necessary context without fluff.

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 tool with no output schema, the description is highly complete: it explains what the tool does, its constraints, how to use it (browser-based), and when to use alternatives. There are no obvious gaps for an AI agent to invoke 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?

The schema already describes the single 'query' parameter as '検索語（英語のみ有効）', and the description reinforces this English-only constraint. Since schema description coverage is 100%, the description adds no significant new parameter-level meaning beyond restating the constraint; the baseline is 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 uses a specific verb and resource: 'assemble the search URL' for the Marginalia search engine. It clearly differentiates from siblings by describing Marginalia's niche (favoring low-commercial personal sites and old pages) and explicitly contrasting with wayback_* tools.

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 gives explicit when-to-use guidance: it states the tool is for generating Marginalia search URLs, and provides clear exclusions—Japanese queries yield no results, results should not be auto-fetched (browser viewing is expected), and for Japanese old-site bodies one should use wayback_* tools instead. This directly names alternatives.

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 disclosure burden. It transparently states that the tool returns a procedure document rather than performing the search itself, and explicitly says to call it first. It does not detail the document's structure or failure modes, but for this simple meta-tool the description is sufficiently honest about its nature.

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 is two compact sentences, front-loading the core purpose and then immediately giving usage direction. Every clause earns its place; no fluff or repetition.

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 the tool's simplicity (one optional parameter, no output schema, no annotations), the description fully covers what it does, when to use it, and what it returns. It provides enough context for an agent to invoke it correctly without needing further details.

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 parameter 'topic' is already fully described as '探したい主題（あれば手順を具体化する）'. The main description adds no extra meaning beyond what the schema provides, so the baseline score 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 uses a specific verb '返す' and clearly states it provides a '手順書' for discovering obscure retro Japanese personal sites, which distinguishes it from sibling tools that directly execute searches or fetch pages. It also explicitly frames itself as a strategic entry point with 'どのツールをどの順で使うか迷ったとき、最初にこれを呼ぶ'.

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 gives a clear usage context: 'どのツールをどの順で使うか迷ったとき' (when unsure which tool to use in what order) and instructs the agent to call this first. It does not name specific alternative tools or exclusion criteria, but the guidance is direct and 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 full burden. It discloses that WARP search results are JavaScript-rendered and the internal API returns 403, meaning HTTP retrieval is impossible, and that the tool only returns a URL and instructions. It also mentions the 2002 coverage limit. This is strong transparency, though it does not cover every possible edge case.

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 is concise and well-structured, with the purpose stated first, followed by constraints clearly marked with 【制約】. Each sentence adds value, with no wasted words.

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 URL-building tool, the description is complete: it explains what the tool does, what it returns, and key constraints. It lacks an explicit output schema but compensates by describing the returned content (URL and instructions). Minor ambiguity about whether the URL targets the WARP search interface or a specific result page could be clarified, but overall it is sufficient.

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 both parameters (keyword, includeInLibrary) are already documented in the schema. The description does not add additional parameter-level details beyond what the schema provides, so the baseline score of 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?

The description states a specific verb ('組み立てる') and resource ('国立国会図書館ウェブアーカイブ（WARP）の検索 URL'), and clearly scopes it to Japanese sites. It distinguishes itself from sibling tools by explicitly saying it only returns a URL and browsing instructions, not fetching results.

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 provides clear usage context: it is for generating WARP search URLs, and it warns that HTTP fetching will not work due to JS rendering and 403 blocking, implying users should use a browser. It also notes the 2002 collection start, suggesting limitations for 1990s pages, though it does not explicitly name alternatives.

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 provided, the description carries the full burden of behavioral disclosure. It discloses its domain-based enumeration nature and date filtering, but does not mention output format, pagination, rate limits, or other operational behaviors. The key caveat (not full-text) is present, but more detail on what the API returns would improve transparency.

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 is three sentences long, front-loaded with the primary action, followed by a use-case scenario and a critical caveat. Every sentence earns its place with no unnecessary information, making it well-structured and concise.

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?

The schema covers all parameters, and the description provides important context about when to use the tool and its limitation as a domain-based enumerator. However, since there is no output schema, the description should ideally state what the tool returns (e.g., a list of URLs) to be fully complete. This omission prevents a higher score.

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 all seven parameters well. The description reinforces the meaning of the url parameter (domain or path) and the date-based parameters (from/to), but does not add significant semantic value beyond the schema, fitting the baseline of 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 clearly states the tool's function: using the Internet Archive CDX API to enumerate URLs under a domain or path with date filtering. It also distinguishes itself from full-text search, differentiating it from sibling search tools like warp_search_url and marginalia_search_url.

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 provides clear context for when to use the tool: as a starting point for finding old personal sites that have disappeared from Google's index. It also explicitly states that it is not a full-text search and cannot search by content, giving a decisive exclusion. However, it does not explicitly name a sibling alternative for content-based search.

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 provided, the description carries the full burden. It discloses that the tool returns raw HTML without the Wayback toolbar and gives a practical tip about using raw=true when text is garbled. This adds meaningful behavioral context beyond just 'fetch', though the default output format is not explicitly stated.

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 is three sentences, front-loaded with the main purpose, followed by suitability and a troubleshooting tip. Every sentence earns its place and there is no redundant 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 simple read-only fetch tool with four parameters and no output schema, the description covers the purpose, a key behavioral detail (no toolbar), a use case, and a parameter-specific tip. It does not mention error behavior or the exact return format, but the schema already documents parameter details and the tool is straightforward.

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 adds value by explaining the raw parameter in a usage context (use raw=true when garbled), which is not present in the schema. This tips the score above 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 specific verb '取得する' (fetch) with a clear resource '保存済みの古いページ本文' (archived page body). It distinguishes itself from sibling tools like wayback_cdx_search (searching snapshots) and wayback_outlinks (extracting links), and even mentions the absence of the Wayback toolbar, which is a specific trait.

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 provides clear context by stating it is suitable for confirming page content and converting to text, which implies when to use it. It does not explicitly name alternatives or exclusions, but the context is sufficient for an AI agent to choose this over related tools.

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 of behavioral disclosure. It clearly states the core action (extract outlinks) and explains the intended recursive usage pattern, which adds context beyond the tool name. However, it does not disclose output format, failure conditions, or any limitations, leaving some transparency gaps.

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 is three sentences: the first states the core function, the second provides strategic rationale, and the third specifies effective page types. Each sentence earns its place and the information is front-loaded, though the middle sentence is somewhat long and expository.

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 tool with 4 parameters and no output schema, the description adequately covers the 'why' and 'when' but omits details about what the returned data looks like or how pagination/limit behave. This leaves the agent without full expectations for the tool's outputs, so while sufficient for basic use, it is not fully 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?

Schema coverage is 100% for all 4 parameters, providing a baseline of 3. The description enhances parameter understanding by emphasizing that the 'url' should be a link collection page and that 'externalOnly' (default true) aligns with the goal of finding sites not indexed by search engines, thereby adding meaningful guidance beyond the schema's 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 clearly states the tool's function ('extract external links from saved pages') and places it in the context of 90s-era site discovery via mutual links and web rings, distinguishing it from general search or page-fetching tools. This it unequivocally separates it from siblings like wayback_fetch_page or wayback_cdx_search.

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 guidance is given on when to use: it is described as the most powerful way to reach obscure old sites and is highly effective on link collection, web ring, antenna, and ranking pages. The description does not explicitly name alternative tools, but it contrasts with search engines and implies a strategy of iterative traversal, offering clear situational context.

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?

The description discloses that the tool returns the closest snapshot relative to the given timestamp and only one result. However, it does not describe the return format, error behavior if no snapshot exists, or any rate constraints. With no annotations provided, the description carries the full burden, and this omission leaves some behavioral ambiguity.

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 is two sentences, front-loaded with the core action, and contains no filler. Every clause serves a purpose, making it highly concise and well-structured.

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?

The description covers purpose, usage context, and the snapshot selection rule, but it lacks an explicit statement of what the tool returns (e.g., snapshot URL vs. metadata) and how it signals absence. Given no output schema and no annotations, this is a noticeable gap, though the tool is simple.

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 input schema already provides complete descriptions for both parameters (url and timestamp), including timestamp formats and default behavior. The description does not add parameter-specific semantics beyond the schema, 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 description explicitly states that the tool checks whether a URL is archived in the Internet Archive and retrieves the single snapshot closest to a specified time. This is a specific verb-resource-scope combination, clearly distinguishing it from sibling tools like wayback_fetch_page or wayback_cdx_search.

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 provides a clear use case: when an old URL is known and you want to verify at minimal cost whether it is still accessible. This implies a lightweight check versus more resource-intensive fetch tools, though it does not explicitly name alternatives or exclusions.

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