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 only that the tool retrieves a list, implying a read-only operation but offering no additional context about authentication, rate limits, return format, or any other behavioral traits.

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 single, concise sentence in Japanese that front-loads the essential information. There is no redundant content or speculation, making it highly efficient 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 tool is simple with no parameters and no output schema, but the description does not explain what the returned list contains (e.g., agent IDs, names, statuses). While it is minimally sufficient for a basic getter, the lack of any return-format or usage caveats leaves some ambiguity.

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 the schema coverage is trivially 100%. The description does not need to explain parameter details since there are none. It adds the semantic context that the resource is a list of call agents, which is adequate for a parameterless tool.

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 'コールエージェント一覧を取得する。' clearly states the action (取得する/retrieve) and the specific resource (コールエージェント一覧/call agent list). This is distinct from sibling tools such as get_optimization_result or get_business_overview, which target different resources.

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. It simply states what it does, without any mention of appropriate scenarios, exclusions, or 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 for behavioral disclosure. It only states that it retrieves data and explains the 'period' argument; it does not mention any side effects, permissions, response format, or whether results are computed live. This is minimal behavioral transparency, though nothing contradicts its read-only 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 concise and front-loaded with the primary purpose, followed by a compact Args section. There is no wasted text; every sentence contributes useful 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 1-parameter tool with no output schema, the description gives the core return type (KPIs and alerts) and the aggregation period. It is reasonably complete for an overview tool, though it could define which KPIs or alert types are included. The existence of sibling tools for finer-grained data partially addresses this.

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 provides only a 'period' field with a default and no description (0% coverage). The tool description compensates by explaining the valid values (daily/weekly/monthly) and the default (monthly), adding meaningful semantics beyond the schema. However, it does not explain the exact impact of each period choice.

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 the tool retrieves KPIs and alerts for the entire business (事業全体のKPIとアラートを取得する), which is a specific verb-resource pair. The scope '事業全体' (whole business) distinguishes it from sibling tools like get_project_kpis (project-level) and get_member_kpis (member-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?

The description implies usage for business-wide overview rather than project/member-specific detail, but it does not explicitly name alternatives or state when not to use this tool. The context that it covers 'the entire business' gives a clear sense of scope, but no explicit guidance is 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?

The description implies read-only behavior via '取得する' (retrieve) but does not explicitly disclose side-effect-free status, pagination, ordering, or authentication requirements. Since no annotations are provided, more detail would be expected, though the simple list-retrieval nature mitigates the 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 concise and well-structured: a one-sentence summary followed by a clear Args list. Every piece of information is relevant and no words are wasted.

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 all five parameters and their roles, which is adequate for a list-retrieval tool. It does not explain return values or pagination, but no output schema exists and the tool's output is intuitive. The absence of cross-references to sibling tools 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 description compensates for the 0% schema description coverage by explaining each parameter's purpose, including allowed values for status and category and the default for overdue_only. This adds meaningful semantics beyond the bare schema titles and types.

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 gets a list of customer feedbacks with a specific verb and resource. It does not explicitly distinguish itself from sibling tools like get_overdue_feedbacks, but the filter parameters imply a broader retrieval scope.

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?

No guidance is provided on when to use this tool versus alternatives such as get_overdue_feedbacks or other get_* tools. The description only lists parameters without explaining use cases or exclusions.

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 aggregation period options (daily/weekly/monthly) and default, but does not describe the return structure, scope of 'members', or any read-only guarantees. The behavior is implied but not fully transparent.

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, using one sentence for purpose and a compact Args block. Every word earns its place, and the most important information is front-loaded.

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 getter with no output schema and no annotations, the description provides the essential parameters and default behavior. However, it lacks details about what KPI fields are returned, whether filtering is possible, and how member scope is determined, leaving some ambiguity for an agent.

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 parameter descriptions (0% coverage), so the description must compensate. It explains period's allowed values and default, and clarifies project_name is required. This adds meaningful semantics beyond the raw 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 member-level KPIs (メンバー別のKPIを取得する), specifying the resource and scope. This distinguishes it from sibling tools like get_project_kpis and get_business_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?

No guidance is provided on when to use this tool versus alternatives such as get_project_kpis. The only usage-related information is the period parameter and its default, 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?

There are no annotations, so the description must carry the full burden of behavioral disclosure. It only mentions retrieving history and provides parameter meanings, but does not discuss ordering, permissions, side effects, or return structure. This is insufficient for a tool with no safety 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 a single sentence followed by a compact argument list, with no filler. It front-loads the main purpose and each parameter line is concise and directly relevant.

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 output schema, the description does not explain what fields the returned history contains, nor any ordering or default behavior beyond the parameter defaults. While the core purpose is clear, the lack of return-value details and edge-case information leaves moderate gaps.

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 provides only types and defaults, so the description adds valuable meaning by explaining target_month as a filter in YYYY-MM format, skip as a skip count, and limit as a maximum result count. This compensates for the schema's 0% description coverage.

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 'アサイン最適化の実行履歴を取得する' (get execution history of assignment optimization), specifying the verb, resource, and scope. It is distinct from sibling tools like get_optimization_result by focusing on history, although it does not explicitly compare itself to alternatives.

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?

No guidance is provided about when to use this tool versus alternatives or when not to use it. The description only states what the tool does, leaving the agent to infer the 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?

With no annotations provided, the description must disclose behavioral details. It merely restates the tool's action ('get details') without describing return structure, side effects, access requirements, or limitations. This is essentially a tautology and provides no added 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 extremely short, with a single sentence and an Args block. It is concise and to the point, with no wasted words. However, the brevity comes at the cost of important context, but that is evaluated under completeness.

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 absence of an output schema and annotations, the description should clarify what 'details' are returned and how run_id is obtained (e.g., from get_optimization_history). It lacks this context, making it insufficient for an agent to confidently invoke the tool correctly in a real workflow.

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 includes an Args section that explains run_id as the '最適化実行ID (UUID)' (optimization execution ID), adding semantic meaning beyond the schema's bare title 'Run Id'. This helps the agent understand the parameter's purpose and format, though it does not cover any additional constraints or relationships.

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 details of an optimization result, with a specific parameter run_id identifying the optimization execution. However, it does not distinguish this from the sibling get_optimization_history, which may also return optimization-related data.

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 no guidance on when to use this tool compared to alternatives such as get_optimization_history or other getter tools. No prerequisites or typical invocation flow are mentioned, leaving the agent to infer usage from the parameter alone.

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, but it only states the action without mentioning return format, read-only nature, or any other behavioral characteristics. It does not contradict any annotations, but it fails to provide meaningful 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 single sentence with no superfluous words. It is front-loaded and highly efficient, earning a top score for conciseness.

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 retrieval tool with no parameters and no output schema, the description is mostly complete. It tells the agent exactly what it retrieves, though the distinction from get_customer_feedbacks could be more explicit to avoid ambiguity.

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 input schema fully covers parameter semantics. The description does not need to add parameter details, and baseline 4 applies as per the rubric.

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 a specific verb (取得する = retrieve) and resource (overdue customer feedback), distinguishing it from the sibling tool get_customer_feedbacks which likely retrieves all feedback. It is immediately obvious what the tool does.

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?

No guidance is given on when to use this tool versus alternatives like get_customer_feedbacks. The 'overdue' qualifier implies a specific use case, but there is no explicit context or exclusion, leaving the agent to infer the appropriate scenario.

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 of behavioral disclosure. The description only says 'get' without detailing return format, error behavior, authorization requirements, or what fields constitute 'detail.' This is a significant gap for a tool with no annotation safety profile.

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 with a single sentence and a brief argument specification. It is front-loaded and contains no filler or 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 tool with no output schema and no annotations, the description does not explain what the returned 'detail' includes or any additional context. With a single parameter it is simple, but the lack of return-value information or behavioral details makes it incomplete for an agent to fully understand the tool's output.

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 only defines project_id as a string, with 0% schema description coverage. The description compensates slightly by explicitly noting 'プロジェクトID (UUID)', which informs the agent of the required UUID format, but it does not elaborate on the parameter's meaning or constraints beyond that.

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 'プロジェクトの詳細情報を取得する' (Get project detail information), which clearly identifies the verb (get) and resource (project detail). It distinguishes from siblings by implying a single project's detailed view, though it does not explicitly differentiate from other getters.

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 like get_project_kpis or get_business_overview. It only restates the purpose without any contextual conditions or exclusions, offering essentially no usage 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?

No annotations are provided, so the description carries the full burden. It only mentions the parameter default and does not disclose any behavioral traits such as whether it is read-only, how aggregation works, or what the resulting data represents.

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 very concise: one sentence plus parameter details. It is front-loaded with the main action and includes no unnecessary 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 single-parameter tool with no output schema, the description is adequate but minimal. It clarifies purpose and parameter, but it does not explain what 'efficiency' means or what the response will contain, leaving some ambiguity.

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 compensates by explaining the 'period' parameter: aggregation period (daily/weekly/monthly) with a default of monthly. This adds meaning beyond the bare schema definition.

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 retrieves efficiency metrics for each project ('プロジェクト別の効率指標を取得する'). It uses a specific verb and resource, but the term 'efficiency indicators' is somewhat vague and does not explicitly distinguish it from sibling tools like get_project_kpis or get_project_detail.

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. It lacks context, usage scenarios, or exclusions, and does not mention any related sibling 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?

The description implies a read-only operation through '取得する' and documents the period parameter, providing some behavioral context. However, with no annotations, it does not disclose return format, aggregation behavior, or potential edge cases, leaving the transparency burden only partially met.

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: a single purpose sentence followed by a compact Args block. Every word contributes to understanding, with no redundancy or 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?

For a single-parameter getter, the core function is clear, but the absence of an output schema means the description should explain what data is returned. It does not mention response structure or limitations, requiring the agent to infer the output.

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 only provides a default value, so the description compensates by listing valid period values (daily/weekly/monthly) and clarifying that it is the aggregation interval. This adds meaningful semantics 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 that the tool retrieves KPI achievement rates by project ('プロジェクト別のKPI達成率を取得する'), using a specific verb and resource. It does not explicitly differentiate from sibling tools such as get_member_kpis or get_project_efficiency, but the 'by project' scope gives adequate clarity.

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?

No guidance is provided on when to use this tool versus alternatives like get_business_overview or get_project_efficiency. The description only covers the period parameter and does not mention use cases, exclusions, or preferred scenarios.

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 present, but the description discloses some behavioral aspects: the default for is_active (True), filtering by status, and pagination via skip/limit. However, it does not describe the return format or any side effects, which is a gap for a tool with no output schema.

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 an Args block, front-loading the main purpose. The main sentence is a bit tautological with the tool name, but the parameter details justify the length.

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 list tool with no output schema, the description should explain what the returned project objects look like. It does not, leaving the output shape ambiguous. The parameter details are solid, but the lack of return value documentation 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?

The input schema has 0% description coverage, but the description provides meaningful definitions for all four parameters: status enum values, is_active default, skip count, and limit. This is essential for correct invocation.

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 'Get project list' and then details filtering parameters, making the tool's purpose evident. It differentiates from siblings like get_project_detail by the list scope, though it does not explicitly name alternatives.

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?

No guidance is provided on when to use this tool versus alternatives. The description only explains what the tool does and its parameters, without any contextual or exclusionary advice.

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 burden. It adds useful context about the deal field's content and the meaning of null (no deal linked), which is beyond the schema. However, it does not disclose read-only status, pagination behavior, or potential performance implications, leaving some behavioral aspects unclear.

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 and a list of parameters, each earning its place. It is concise but informative, though the Args block adds a bit of length; no redundant content is present.

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 no output schema and no annotations, the description covers essential return behavior: the combined project and deal data, what the deal field contains, and null handling. It also covers all parameters. It could be more explicit about default behaviors (e.g., null status meaning 'no filter'), but it is reasonably complete for a list-fetching 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?

Schema description coverage is 0%, and the description's Args section provides meaning for all four parameters: status (filter by statuses), is_active (active only), skip (offset), and limit (max results). This compensates for the schema's lack of descriptions and adds clear semantics beyond parameter names and types.

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 a list of projects joined with TRUE OS deal information (contract amounts), specifying the exact resource and action. It distinguishes itself from siblings like get_project_list (projects without deal info) and get_true_os_deals (deals only) by the combination of projects and deals.

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 projects with deal information but does not explicitly state when to prefer this over alternatives or mention exclusions. It lacks direct guidance such as 'use get_project_list for projects without deal data' or 'use get_true_os_deals for deal-only queries.'

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 only states 'get' (acquire), implying a read operation, but does not explain whether it is read-only, what data it returns, or any special behavior such as rate limits or data freshness. This is minimal 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 a single concise sentence that immediately states the core purpose. There is no redundant or filler content, making it highly 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?

The tool has no output schema, so the description should clarify what the utilization rate means, the time range, or the output format. It only provides the basic 'get utilization rate' statement, which is insufficient for a fully context-aware agent, especially given sibling tools with overlapping data.

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 description's lack of parameter detail is not a deficiency. Per the rubric, a baseline of 4 is appropriate when no parameters exist.

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 action ('取得する') and resource ('リソース（エージェント）の稼働率'), which is specific and distinct from sibling tools like get_work_time_summary or get_member_kpis. It directly conveys what the tool does.

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. It does not mention any exclusions, prerequisites, or typical scenarios, leaving the agent to infer usage from the tool name and description alone.

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 disclose behavioral traits. It implies a read-only fetch ('取得') but does not mention return format, pagination, or any side effects. The parameter list is about syntax, not 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?

The description is concise and front-loaded with the main purpose. The Args section is redundant with the schema but useful for clarity. No unnecessary prose.

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?

Without an output schema, the description should explain what the response contains, but it does not. It also lacks context about the schedule domain or any usage scenarios. For a simple retrieval tool, this is a notable 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 description adds meaning beyond the schema: it specifies date format (YYYY-MM-DD), marks start/end dates as required, and clarifies user_id as a filter with UUID type. Schema descriptions are absent (0% coverage), so this compensation is valuable.

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 a list of schedules ('スケジュール一覧を取得する'), which is a specific verb+resource. It is distinct from sibling tools by resource, though it does not explicitly differentiate from 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?

No guidance is provided on when to use this tool versus alternatives (e.g., other get_* tools). The description only lists parameters, not usage context or exclusions.

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 clearly indicates a read operation (取得する), describes the returned data scope (contract amount, status, phase), and specifies filtering behavior. It does not mention potential rate limits or authentication, but for a simple read/list tool, this level of disclosure is adequate.

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: one introductory paragraph stating purpose and scope, followed by a structured Args list. Every sentence adds value, and 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?

Given the tool has 3 optional parameters and no output schema, the description covers the main aspects: purpose, return content, and filter options. It omits details like return format or error handling, but for a straightforward list retrieval tool with no annotations, it is reasonably complete. The distinction from get_projects_with_deals further enriches context.

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 fully compensates by documenting all three parameters in an Args section. It provides allowed values for status and phase, and defaults for product and phase, adding significant meaning 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 explicitly states it retrieves a list of all deals (ディール一覧) from TRUE OS Gateway, using the verb '取得する' and clearly defines the resource. It also distinguishes itself from sibling tools by noting it retrieves deals regardless of project association, setting it apart from get_projects_with_deals.

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 that this tool is for retrieving all deals without project linkage, and mentions available filters (status, product, phase). It does not explicitly name an alternative tool for project-specific deals, but the sibling name get_projects_with_deals implies that use case. This is clear context without explicit exclusions.

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 only says 'get' (implying read-only) but does not mention what the summary contains, whether it covers all members or specific ones, how data is aggregated, or any limitations. No auth, rate limits, or return format details are given.

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 very concise, with a single purpose statement and parameter list. It is appropriately front-loaded and contains no wasted words. However, it is slightly under-specified, but that is a completeness issue, not a conciseness one.

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 tool is relatively simple (2 params, no output schema, no annotations), but the description is too sparse. It does not explain what the 'work time summary' includes (e.g., daily totals, per-person breakdown), what time period is covered beyond the month, or what the response structure looks like. An agent would struggle to know what to expect from the call.

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 explain the parameters. It does provide useful context: 'year: 年 (例: 2026)' and 'month: 月 (1-12)', clarifying the expected format and range for month. This goes beyond the schema's type-only definitions, compensating for the lack of property 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: '勤務時間サマリーを取得する' (Get work time summary), which is a specific verb+resource. It is distinct from sibling tools like get_project_kpis or get_member_kpis, though it does not explicitly differentiate itself from 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?

There is no guidance on when to use this tool versus alternatives. The description only lists parameters without any context about typical use cases, prerequisites, or exclusions.

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