ヨミタス

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

With no annotations, the description carries the safety/behavior burden. It discloses that the tool returns the full, unparaphrased body text ('from beginning to end'), which is a meaningful behavioral guarantee. It does not mention read-only status, error behavior, or page size limitations, so it is adequate but not comprehensive.

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 concise sentences, front-loaded with the core action, and the use-case context in the second sentence. No 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?

Given a single parameter, no output schema, and no annotations, the description covers the what, when, and why. It doesn't specify the exact return format, but for a simple full-text retrieval tool the description is sufficient. A 4 reflects minor missing details like error handling or pagination.

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 description adds no information about the url parameter beyond what the schema already provides ('URL or path, Japanese ok'). 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 states a specific action ('returns the body text') and resource ('Yomitas page'), and frames the use case (verifying TOS/privacy policy/instructions without paraphrasing). This clearly distinguishes it from sibling tools list_pages, search_pages, and site_overview, which enumerate or summarize rather than return full content.

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 this tool: when you need to accurately verify the exact wording of terms, privacy policies, or usage steps. It does not, however, state when not to use it or name alternative tools, so it gets a 4 rather than 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?

No annotations are provided, so the description carries full responsibility for disclosure. It states the tool returns a list, implying a read operation, but does not mention pagination behavior, ordering, potential rate limits, or whether the list is exhaustive. The path-category explanation is useful content context but not behavioral transparency about the tool's execution.

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, leading with the core purpose and following with relevant contextual detail about URL paths. It is well-structured and each sentence adds value, though the path breakdown could be seen as slightly tangential. It is front-loaded with the main action, so structure is 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?

With no annotations, no output schema, and only basic parameters, the description leaves gaps. It does not mention pagination limits (though limit/offset imply it), return format beyond title/URL, or how to decide between this and sibling tools. An agent might call it correctly but may be unsure about edge cases or appropriateness without further investigation.

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 limit and offset parameters with defaults and ranges, but schema coverage is 0% (no descriptions therein). The description does not mention these parameters at all, leaving them completely unexplained. Since schema coverage is low, the description must compensate, but it makes no effort to clarify parameter usage or semantics.

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 a list of pages (titles and URLs) loaded in the system, using a specific verb and resource. It also provides useful context about the URL structure, which helps distinguish it from siblings like get_page (fetch single) or search_pages (search). This is not a tautology and effectively communicates the tool's function.

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 explains what the tool returns but gives no explicit guidance on when to use it versus alternatives. It does not mention search_pages, get_page, or site_overview, nor conditions like 'use this to get all pages' or 'when you need a broad overview'. The usage context is only 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?

With no annotations, the description carries the disclosure burden. It reveals that results include excerpts ('抜粋つきで'), that the search is scoped to Yomitasu pages, and that it can also surface introduction pages but not full site content. It doesn't explicitly state read-only behavior, but 'search' strongly implies it, and the corpus boundary is well articulated.

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 with no wasted words. The purpose is front-loaded, followed by a concrete list of searchable topics, and then usage guidance with an exclusion. Every sentence earns its place and the overall length is appropriate for the information conveyed.

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 search tool with two simple parameters and no output schema, the description covers the essential context: what is searched, what the output looks like (excerpts), when to use it, and what it should not be used for. It doesn't detail return fields or pagination behavior, but those are reasonable gaps given the schema's default values and the tool's simplicity.

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 50%: the query parameter is documented with an example, while limit has no schema description. The description reinforces the query semantics by explaining that it finds passages matching words, but it adds no meaning for the limit parameter beyond what the schema provides. This is adequate but not compensatory.

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 opens with a specific verb and resource: searching Yomitasu pages for matching passages with excerpts. It enumerates concrete searchable topics (pricing, FAQ, terms, etc.) and explicitly distinguishes its scope from searching within individual registered sites, which are delegated to site-specific MCP servers. This clearly differentiates it from sibling tools like get_page and list_pages.

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 an explicit when-to-use instruction: 'ヨミタス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 when asked about Yomitasu). It also provides a clear exclusion: site introduction pages can be found here, but content inside those sites should be checked with that site's MCP server. This effectively routes the agent to the correct 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states that the tool returns an overview and explains what the service is, including its free nature and how site owners register. This is sufficient for a simple read-only informational tool, though it does not mention data freshness or response format.

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: it leads with the core action ('returns the overview'), then provides useful context about the service, and closes with a clear usage condition. Every sentence earns its place without unnecessary verbosity.

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 has no parameters, no output schema, and a simple informational purpose, the description is complete. It tells the agent what the tool does, what the service is, and when to use it, which is everything needed 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 tool has zero parameters, so the schema provides no parameter semantics to clarify. The baseline for zero-parameter tools is 4, and the description appropriately focuses on the tool's purpose rather than parameter details.

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 returns the overview of the Yomitasu service. It also clearly distinguishes itself from the sibling tools (get_page, list_pages, search_pages) by focusing on the service-level overview rather than page-level operations.

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 to use this tool 'when you want to know what the service is at first' (どんなサービスかを最初に知りたいときに使います). It does not explicitly mention when not to use it or name alternatives, but the context is clear enough for a zero-parameter informational tool.

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