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

With no annotations, the description carries the full burden. It discloses the return structure (dictionary of name, path, method, parameters, response, auth, plans) and implies a read-only lookup, but does not explicitly state it is non-mutating, nor cover error conditions or rate limits. It adds useful context beyond the schema but leaves some aspects implicit.

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 with a summary line, Args, and Returns sections. It is a bit longer than strictly necessary, but the api_version guidance is valuable and earns its place. No redundancy with the schema.

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 2-parameter tool with an output schema, the description covers purpose, parameter semantics, and return values. However, it lacks any mention of when to prefer this tool over search_endpoints or get_info, and it does not address potential errors or prerequisites (e.g., auth). These gaps prevent 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 0%, so the description must compensate. It does exceptionally well: endpoint_name is illustrated with V2/V1 examples (eq-master, daily_quotes), and api_version comes with decision rules based on conversation context and endpoint naming patterns. This goes far beyond the bare 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 clearly states the tool retrieves detailed information for a specified endpoint ('指定されたエンドポイントの詳細情報を取得する'), with a specific verb and resource. It does not explicitly distinguish from sibling tools like search_endpoints or get_info, so it misses the top score for 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?

There is implied usage (need details for a known endpoint) and practical guidance for choosing api_version based on V1/V2 context ('V1のエンドポイントパス...が含まれる場合は'v1'を指定'). However, it does not provide explicit when-to-use vs alternatives (e.g., search_endpoints) or exclusions, so it only reaches the 'implied usage' level.

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 the return dictionary fields, including a 'cached' flag indicating potential caching behavior, but does not mention authentication, error handling, or rate limits. The safety profile is implied as read-only, but 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 well-structured with a brief purpose statement, usage note, and separately labeled Args/Returns sections. It is not overly verbose, and each section contributes necessary information. Slightly longer than the ideal two-sentence format, 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 simple tool with one parameter and no output schema, the description covers the essential aspects: purpose, usage, parameter example, and return fields. It lacks explicit error or authentication details, but overall it gives an agent enough to select and invoke the tool 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 has zero description coverage, but the description defines the 'path' parameter with an example ('/spec/mkt-cal/holiday-division'), adding meaning that the schema lacks. It does not go into exhaustive detail about path construction, but the example is sufficient for most cases.

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 retrieves a Specification page for a given path, and explicitly notes it can also fetch reference data pages (e.g., holiday divisions, market codes). This distinguishes it from sibling tools like describe_endpoint by emphasizing raw page retrieval and link-following scenarios.

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 usage context: 'Use when following links in Markdown to obtain additional information.' However, it does not explicitly mention alternatives like describe_endpoint or state when not to use this tool, so it falls short of a perfect score.

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 burden. It discloses that the tool returns a dictionary with official page links and LLM answer instructions, and emphasizes it is an accurate source. However, it does not mention potential limitations like data freshness, but this is adequate for a simple info 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?

The description is well-structured with a sample list and Args/Returns sections, and it front-loads the core purpose. It is somewhat lengthy due to the exhaustive list, but each line adds useful guidance and 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?

This is a simple tool with one optional parameter and no annotations. The description covers the purpose, usage boundaries, parameter meaning, and return format, making it sufficiently complete. The presence of an output schema and no nested objects reduces the need for additional 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?

The input schema has 0% description coverage, but the description's Args section explains 'query' with examples ('Premiumプランの料金は？'). It adds concrete meaning beyond the schema. However, it doesn't clarify the optional null case or what happens if query is omitted, a minor 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 explicitly states this tool answers questions outside the API specification scope, listing concrete categories such as pricing, contracts, and support. It clearly distinguishes itself from siblings by naming search_endpoints as the alternative, making the purpose 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 guidance: it lists specific question types and says to use this tool instead of other tools like search_endpoints. It also defines the boundary as 'outside API spec', giving clear when-to-use and when-not-to-use 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?

With no annotations, the description carries the full behavioral burden. It discloses the conditional behavior (if pattern_name is omitted, returns all patterns) and notes the return type as a dictionary. However, it does not mention error conditions, permissions, or side effects, leaving some behavioral 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 concise and well-structured with a clear summary line, Args section, and Returns section. It is free of unnecessary words and every sentence contributes to understanding the tool.

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 simple single-parameter tool and the presence of an output schema, the description covers the main behavior and parameter semantics effectively. It lacks explicit usage differentiation from siblings and error behavior details, but the essentials are present, making it reasonably complete for a getter 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?

The input schema has no descriptions, so the description's docstring is the only source of parameter meaning. It clearly explains pattern_name and the effect of not specifying it (returns a list of all patterns), which compensates for the 0% schema coverage. This adds meaningful value 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 clearly states the tool's purpose with a specific verb and resource: '実装パターン情報を取得する' (gets implementation pattern information). However, it does not explicitly differentiate itself from sibling tools like get_info, so it misses the top score for 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 description provides no guidance on when to use this tool versus alternatives such as get_info or describe_endpoint. It only explains the pattern_name parameter and its default behavior, which is parameter semantics rather than usage 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only mentions that the tool returns a status dictionary, but does not disclose failure behavior (e.g., what happens if the server is down), side effects, or any safety guarantees. This is insufficient given the lack of annotations.

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 extremely concise, consisting of two short sentences and a Returns section. Every sentence serves a purpose: it states what the tool is for and what it returns. No unnecessary wording.

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 (zero parameters) and the presence of an output schema, the description covers the core essentials. It could be improved by explaining why one would run a health check or what actions to take based on the result, but these are not strictly necessary for a basic health check 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?

The tool has no parameters, so the baseline of 4 applies. The description does not need to add parameter information, and it does not introduce any confusion or redundancy.

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 it is a tool for checking whether the server is operating normally, using a specific verb ('確認する') and resource (server health). This distinguishes it from sibling tools like search_endpoints or describe_endpoint, which focus on API metadata rather than server status.

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 implies usage for health checks ('ヘルスチェック用') but does not explicitly mention alternatives, when not to use it, or provide any exclusion criteria. It provides basic context but lacks the explicit guidance seen in higher-scoring examples.

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 full responsibility for disclosing behavior. It explains that the tool returns a dictionary containing Markdown and guidance to the V2 spec page, and clarifies the optional parameter behavior. It does not cover auth or rate limits, but for a guide tool this is acceptable.

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 with an introductory sentence, usage context, Args, and Returns sections. It is front-loaded with the purpose and does not contain redundant information, though it is slightly verbose.

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 provides sufficient information for an agent to invoke the tool correctly: purpose, parameter semantics, and return format. It does not mention error handling, but given the simple nature of the tool, the provided details are adequate.

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 has zero description coverage for v1_endpoint, but the description compensates fully by defining it as an endpoint path or keyword, providing concrete examples ('/v1/prices/daily_quotes'), and stating the default behavior when omitted. This adds substantial 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 clearly states the tool provides a migration guide from V1 to V2 API, using the specific verb 'provide' and resource 'migration guide'. It distinguishes itself from sibling tools by focusing on endpoint correspondence and redirecting to V2 specification pages, which is a unique 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 explicitly defines the target scenario: 'when users using V1 API migrate to V2 API', and explains the behavior when v1_endpoint is omitted. It does not explicitly mention alternatives, but the sibling tool names make the contextual differentiation clear.

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 full burden. It discloses that search covers endpoint name, path, and description, and describes the return structure as a dictionary with a count and results array. It also explains the api_version decision rule, which is useful 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 a compact structured block with Args and Returns sections, no redundant text, and every clause adds information. It is appropriately sized for the tool's complexity.

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, all three parameters, and return type, and an output schema exists. It is sufficient for a search tool, though minor details like case-sensitivity or sorting are not mentioned, slightly preventing a perfect 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 provides only titles and defaults with 0% description coverage. The description fully compensates: keyword scope is specified (searches name/path/description), category includes example filters (auth, listed, prices, fins), and api_version gets a clear decision procedure. This goes well 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 opens with 'エンドポイントをキーワードとカテゴリで検索する' (Search endpoints by keyword and category), clearly stating the action and resource. This distinguishes it from siblings like describe_endpoint and health_check, which serve different purposes.

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 does not explicitly mention alternatives or when not to use this tool. However, it provides detailed guidance on selecting api_version based on conversation context (V1 vs V2), which aids correct invocation. No when-not-to-use or sibling differentiation is present.

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