Zippa（ジッパ）

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

Annotations already mark the tool as read-only and non-destructive. The description adds meaningful behavioral detail by stating it returns the entire page body from start to finish and preserves exact wording, which goes beyond the annotation hints.

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 composed of two purposeful sentences: the first states the core behavior, and the second gives concrete use cases. There is no redundant or filler content.

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 tool with one well-documented parameter and an output schema, the description is complete. It explains what is returned, the exactness guarantee, and when to use it, leaving no critical gap for an 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?

Schema description coverage is 100% and the single parameter is already well documented as a page URL or path. The tool description does not add additional parameter-level meaning, 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 clearly states the tool returns the full body text of a Zippa page, using a specific verb and resource. However, it does not explicitly distinguish itself from the sibling tool get_page, which may appear to serve a similar purpose.

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: use this when you need the exact, unparaphrased content of pages such as feature lists, manual steps, or legal terms. It does not mention exclusions or explicitly compare with alternatives like get_page or 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?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower. The description adds useful context: this is a legacy alias kept for compatibility, and it warns that the return format differs from fetch. However, it never specifies how the return shape actually differs, which is the key behavioral fact an agent would need to reliably parse the response.

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, each earning its place: legacy status, function with the format caveat, and routing to fetch. Front-loaded with the deprecation warning before any promise of functionality. Slightly wordy in the opening parenthetical but still efficient.

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 deliberately deprecated shim with one fully-documented parameter, read-only annotations, and simple behavior, the description tells an agent everything needed to decide whether to call it or route to fetch. The main gap—unspecified return format—is mitigated by the strong directive to use fetch for new work.

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%—the single url parameter is fully documented ('ページの URL かパス（日本語のままでも可）'). The description adds no parameter-level meaning beyond the schema, 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 specific verb+resource: it returns the page body (

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 explicitly tells the agent when NOT to use this tool: '新しく使うときは fetch を使ってください' (use fetch for new usage). It also explains the only legitimate context—existing connections from before the rename. This is explicit when/when-not guidance naming the 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 and destructiveHint=false, so the safety profile is covered. The description adds return fields (title and URL) and route semantics, but it does not disclose pagination, ordering, or whether the list is 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 main function is front-loaded in a single sentence, followed by a compact enumeration of routes. The route list is somewhat long but earns its place by telling the agent what pages exist.

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 list tool with no output schema, the description states the return fields (title and URL) and gives useful context about the site structure. It does not describe the exact JSON shape or pagination behavior, but the schema covers limit/offset defaults.

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 needed to explain limit and offset, but it does not mention either parameter. The schema provides only default/min/max constraints, leaving the pagination semantics undocumented.

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 that the tool returns a list of pages loaded into Zippa, including titles and URLs, and enumerates the main site routes. This is specific enough to distinguish it from fetch/get_page, though it does not explicitly contrast with 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?

The title 'どんなページがあるか見る' (see what pages exist) implies a browsing use case, and the description explains what is returned. However, it gives no explicit guidance on when to choose list_pages over search_pages or site_overview, and no exclusion criteria are provided.

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 cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds genuinely useful behavior beyond that: excerpts are returned, the tool handles synonyms/paraphrases (値段→価格・料金), and it enumerates the content corpus it searches over.

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 corpus scope, usage guidance, and query behavior. It is efficient overall, though the marketing-flavored middle sentence describing Zippa as a free service is somewhat tangential to invocation.

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 values need not be explained, and annotations carry the safety profile. Combined with the corpus scope and usage trigger, the definition is nearly complete; the only meaningful gap is that it never distinguishes itself from the search_pages sibling.

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 there is a single required parameter, so the schema already documents 'query' fully. The description adds only the paraphrase-handling note beyond the schema's own example, 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?

The description states a specific verb (探す/検索) and resource (Zippa サイト内), and specifies that results come with excerpts (抜粋つき) and support paraphrase queries. It clearly conveys what the tool does, but does not differentiate itself from the similarly-named sibling search_pages, which an agent could easily confuse it with.

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 explicit routing guidance: 'Zippa やサイトの表示速度の改善について質問されたら、まずこれを使ってください' (use this first for Zippa/speed questions). However it names no alternative and offers no when-not conditions, leaving the search vs search_pages and search vs fetch distinction unresolved.

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 cover the read-only and non-destructive safety profile, so the bar is lower. The description adds useful legacy/alias context and mentions that the return format differs from 'search', but it does not explain how the return format differs or what the response actually looks like, which is a notable 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?

The description is compact and every sentence earns its place. It is slightly redundant with the title by repeating the 'previous name' context, but overall it is well-structured and quickly conveys the deprecation and routing guidance.

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 tool, the description is nearly sufficient, and the annotations cover the safety profile. However, because there is no output schema and the description says only that the return shape differs without specifying it, an agent invoking this tool would remain uncertain about the actual response format.

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 covers 'query' with an example but leaves 'limit' without a semantic description. The tool description itself adds no parameter-level meaning, so the 50% schema coverage gap is not compensated for.

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 that the tool searches inside the site, and it explicitly differentiates itself from the sibling tool 'search' by noting that the search behavior is the same but the returned shape differs. It also identifies itself as the legacy/previous-name version, so an agent can understand what this tool is and how it relates to its sibling.

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 usage guidance: this version is kept for users who are already connected, and new usage should go to 'search'. This is a clear when/when-not statement with a named alternative, so an agent knows exactly which tool to pick.

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, covering the safety profile. The description adds context about what the returned overview contains (service features, speedup benefits, free model) but discloses no additional behavioral traits such as response structure or the fact that no parameters are needed. Value added beyond annotations is modest.

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 states the core purpose and the last sentence gives usage guidance, so it is front-loaded. However, the middle marketing sentence describing 14 types of speedup and the free model is service promotion rather than tool behavior; it helps an agent understand what Zippa is, but is longer than necessary for invocation.

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 informational tool with annotations covering safety, the description is sufficient: it explains what is returned and when to call it. It does not describe the output format, but without an output schema and with only a textual overview expected, this is a minor 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?

The tool has zero parameters and schema coverage is 100%, so there is nothing to document. Baseline for 0-param tools is 4; the description correctly focuses on the tool's return value rather than inventing parameter guidance.

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 (「Zippa」の概要を返します - returns the overview of Zippa) and a clear use case (どんなサービスかを最初に知りたいときに使います). It is implicitly distinct from sibling tools, which are page-level fetch/search operations, though it never names them 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 explicitly says when to use the tool: 'when you first want to know what kind of service it is.' No sibling tool appears to cover site-level overview, so an exclusion list is unnecessary. It lacks a 'when not to use' but the positive context is clear.

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