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

No annotations are provided, so the description carries the full burden. The description does not disclose whether this action is idempotent, reversible, or requires specific permissions. It only says 'add comment' without mentioning any side effects or constraints.

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 one concise sentence that front-loads the purpose. It is appropriately brief, but could potentially include more context without losing 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?

Given the lack of annotations and output schema, and with three required parameters, the description is insufficient. It does not explain the return value (e.g., comment ID, success message) or any validation constraints on content. The context feels incomplete for an effective tool usage.

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 0%, meaning no parameter descriptions. The description does not add any detail about goal_id, user_id, or content beyond their names. However, the schema itself is clear with three simple string parameters, and required fields are obvious. The description adds no additional meaning, so 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 'ゴールにコメントを追加する。' clearly states the tool's purpose: adding a comment to a goal. It uses a specific verb (add) and resource (goal), which distinguishes it from siblings like get_comments (which retrieves comments) and other goal-related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like get_comments or other action tools. There is no mention of prerequisites (e.g., goal must exist), or when not to use it (e.g., if comments are disabled).

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 mentions that descendants are also completed (子孫も連動), which is a behavioral trait beyond the parameter schema. However, there are no annotations, so the description must carry the full burden. It lacks details on reversibility or confirmation requirements.

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 short (two sentences) and front-loaded with the core action. However, the second sentence adds critical info about side effects, which is good use of space.

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 low complexity (one parameter, no output schema), the description covers the basic function and side effect. However, siblings include 'complete_task' and 'get_goal_detail', and the description does not help differentiate from them beyond the side effect. No information about return values or error states is provided.

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, meaning no parameter descriptions. The tool description adds no semantics for the goal_id parameter beyond what the schema provides (type string, required). Baseline 3 is given because parameter count is low (1) and the purpose is implied.

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 'ゴールを完了にする。子孫も連動。' clearly states the verb 'complete' and the resource 'goal' in Japanese. It also adds that descendants are affected, which distinguishes it from a simple completion action. However, being in Japanese may limit understanding for non-Japanese agents.

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 explicit guidance on when to use this tool vs alternative completion tools like 'complete_task'. The description does not mention prerequisites or scenarios where this tool is preferred.

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 fails to mention that this is a write operation (modifies state), whether the action is reversible, side effects (e.g., changes status), or success/failure outcomes. The description lacks necessary behavioral context for a mutation 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?

Single sentence, highly concise. No wasted words. However, it could benefit from slight expansion to cover usage or behavior without becoming 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?

Given the tool's simplicity (single param, no output schema), the description is incomplete. It lacks behavioral transparency, parameter guidance, and usage context. For a simple tool, more completeness is expected.

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?

With 0% schema description coverage and one parameter (task_id), the description does not explain the parameter's semantics (e.g., format, example, or source). It adds no additional meaning beyond the schema, which only provides name and type.

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 'ToDoタスクを完了にする' clearly states the tool's function: marking a ToDo task as complete. The verb '完了にする' combined with 'ToDoタスク' provides a specific action and resource type. It distinguishes from siblings like 'complete_goal' which is about goals, not tasks.

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 prerequisites (e.g., task must exist) or exclude cases like already completed tasks. No explicit context for usage.

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 does not mention any side effects (none expected for a get operation), auth requirements, rate limits, or pagination. The description is too brief.

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 short, but it is not overly verbose. However, it could be expanded to include more useful information without sacrificing 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?

Given the tool's simplicity (one param, no output schema, no annotations), the description is not complete. It does not mention what the response looks like, whether ordering exists, or if the thread includes all comments.

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% (no descriptions in input schema). The description does not elaborate on the goal_id parameter, so it adds no meaning beyond the schema. The parameter is required but no format or example is given.

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 says 'Retrieve comment thread of a goal' which clearly states the action (get) and resource (comment thread), but it does not differentiate from siblings like add_comment. The verb 'get' is specific enough.

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 on when to use this tool vs alternatives. There is no mention of when not to use it or mention of sibling tools like add_comment for creating comments.

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 provided, so the description carries the full burden. It describes the output (KPI, sub-goals, etc.) but does not disclose any behavioral traits like required permissions, performance implications, or side effects. Given the tool reads data, the lack of destructive hint is not critical, but more context would be beneficial.

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, only one sentence, and front-loads the purpose. It could potentially include more detail without being verbose, but it currently has no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has a single parameter and no output schema, the description is minimally acceptable but lacks explanation of the return format or how it ties into the goal management workflow. It is complete enough for a simple read operation but not fully comprehensive.

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 covers the only parameter (goal_id) with 100% coverage, so the description does not add extra meaning beyond what the schema provides. 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 clearly states the tool retrieves details of a goal, including KPIs, sub-goals, deliverables, and comment count. However, it doesn't differentiate from sibling tools like get_goals, which may also return goal information, so not a 5.

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 use for retrieving comprehensive goal details, but it does not explicitly state when to use this over get_goals or get_kpi_progress, nor does it mention prerequisites or alternatives.

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

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

No annotations provided, so description carries full burden. It describes retrieval behavior and filtering, but does not disclose pagination, sorting, or performance characteristics. For a list tool, basic behavioral traits like result limits or ordering are missing.

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?

Description is brief and front-loaded with the main purpose. It is concise but includes essential filtering info. However, it is in Japanese, which may affect readability for non-Japanese users, but structurally it's 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?

Given the complexity of 6 parameters and no output schema, the description is adequate but incomplete. It does not explain the return format or any constraints like maximum results. With 100% schema coverage, it meets minimum viability but lacks depth for complex filtering.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents each parameter. The description adds no additional meaning beyond summarizing that filters exist. 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?

Description clearly states it retrieves a list of team goals with filtering options. The verb 'get' and resource 'goals' are explicit, and filtering capabilities are listed, distinguishing it from siblings like get_goal_detail (single goal) and get_overdue_goals (filtered subset).

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?

Description implies usage for listing goals with filters, but provides no explicit guidance on when to use this tool versus other sibling tools like get_goal_detail or get_phase_summary. No alternatives or exclusions are mentioned.

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 behavioral burden. It only states the tool retrieves data but does not disclose any behavioral traits such as read-only nature, performance implications, or any side effects.

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 in Japanese, which is concise. However, it could benefit from additional context without becoming 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?

Given the tool has 2 parameters, no output schema, and no annotations, the description is minimally adequate but lacks details on return format, filtering behavior, and any prerequisites. Completeness is average for a simple retrieval 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 100%, so both parameters are documented in the schema. The description does not add extra meaning beyond what the schema provides, so 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 that the tool retrieves a list of KPI progress for a team, which is a specific verb-resource pair. While it is clear, it does not differentiate from siblings like get_goal_detail or get_goals, as KPI progress could be related but distinct.

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 on when to use this tool versus alternatives is provided. The description does not mention any context where this tool should be preferred over sibling tools like get_goals or get_phase_summary.

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, but the description does not disclose behavioral traits. It doesn't mention whether results are chronological, whether notifications are marked as read, or any side effects. The description relies entirely on the tool name.

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 in Japanese, which is concise but lacks detail. It is front-loaded but omits critical information that would fit in a few more sentences.

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 that the tool has 3 parameters (2 required), no output schema, and no annotations, the description is insufficient. It only conveys the basic purpose, missing details on parameters, behavior, and usage context. Sibling tools like get_comments suggest a task management context, but the description doesn't leverage 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?

Schema description coverage is 0%, and the description adds no parameter information. It does not explain the purpose of team_id, user_id, or unread_only. For example, it doesn't clarify whether unread_only filters to unread notifications or marks them as read.

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 'ユーザーの通知を取得する' which means 'get user notifications'. It specifies the verb (取得する/get) and resource (通知/notifications), but it lacks clarity on scope (e.g., all notifications or filtered by team?). It does not differentiate from siblings like get_comments or get_goals.

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 on when to use this tool vs alternatives. For example, it doesn't explain how it differs from get_comments or state whether it retrieves all notifications or only for the current user. The required user_id suggests personal scope but is not explicit.

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 fully disclose behavior. It only states the basic function ('retrieve overdue active goals') without any behavioral traits such as data limits, sorting, or side effects. As a read tool, it likely has no destructive effects, but the description does not confirm this or mention any prerequisites.

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, which is concise for a simple tool. However, it is in Japanese, which may limit usability for English-speaking agents, though the context provided by the user is English. The description is appropriately front-loaded with the core function.

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 two optional parameters with zero semantic coverage, the description provides only the bare minimum. It explains the purpose but lacks details on parameter meanings and usage context. The presence of sibling tools like get_goals suggests a need for clearer differentiation, which is missing.

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%, meaning the schema provides zero semantic context for 'team_id' and 'assigned_to'. The description does not explain what these parameters mean (e.g., team_id likely identifies a workspace, assigned_to likely filters by assignee), leaving the agent guessing about their usage.

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 overdue active goals, which is a specific verb+resource combination. It distinguishes itself from siblings like get_goals (which likely retrieves all goals), but doesn't explicitly differentiate from get_goal_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?

No usage guidelines are provided. There is no guidance on when to use this tool vs siblings like get_goals or get_goal_detail, nor any when-not-to-use information.

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 are absent, so the description carries full burden. It indicates a read operation (get) and the scope (summary) but does not disclose behavior like required permissions, data staleness, or pagination. No contradictions with missing 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?

Single sentence, no fluff. Could be slightly clearer by mentioning required parameters, but remains 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 read operation with no output schema, the description is adequate but incomplete. Does not specify what exactly is returned or how to use the phase_id parameter.

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%, meaning the description must compensate. It only adds 'phase' context but does not explain the purpose of team_id or that phase_id is optional. Both parameters are undocumented in description and 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 what the tool does: obtain a phase's goal, KPI, and progress summary. It specifies the resource (phase) and key attributes (goal, KPI, progress), distinguishing it from siblings that focus on individual goals, tasks, or comments.

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 on when to use this tool versus alternatives. For example, get_goals and get_goal_detail are siblings, but the description does not differentiate use cases or mention prerequisites like having a phase_id.

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 provided, so description must fully disclose behavior. It states a GET operation (member list) but doesn't mention if it's read-only, performance implications, or pagination. Lacks safety 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?

Single sentence, no waste. Efficient for a simple tool, but lacks depth that could be added without 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 no output schema and 0% schema coverage, description is too sparse. Agent cannot infer return type, structure, or error handling. Sibling tools suggest a goal/team management domain, but no integration 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 has 1 parameter (team_id) with 0% description coverage, so description must compensate. Description does not explain what team_id is (e.g., string format, ID type) or any constraints. The tool name implies team context, but no semantic clarification for the parameter.

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?

Description 'チームメンバー一覧を取得する' (get team member list) provides a clear verb+resource, but is vague about scope (all members? active?). Purpose is clear but minimal.

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 on when to use this tool vs siblings like get_comments, get_goals. No context on prerequisites or exclusions. Agent has to infer usage from name 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 bears full burden. It indicates read-only behavior, but does not disclose any side effects, authentication needs, or execution contexts. Adequate but minimal.

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?

Single clear sentence, no fluff. Front-loads the key information: what it does and for whom.

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 tool (3 params, no output schema), the description is adequate but doesn't explain return format, pagination, or timezone details. Could be more complete for a production 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 coverage is 100%, so baseline is 3. The description does not add meaning beyond schema; e.g., date is explained as optional defaulting to today, but this is already in the schema. No extra 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 clearly states it retrieves today's ToDo list for a specified user, which is a specific verb-resource combination. It distinguishes from siblings like complete_task and get_goals.

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 when to use (for today's tasks), but does not explicitly state when not to or provide alternatives. Sibling tools suggest other task-related operations, but no direct guidance is given.

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 behavioral burden. The description implies a read operation (get) but does not disclose any side effects, authorization requirements, or limitations. A score of 3 is given because it is not misleading, but lacks detail.

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. It is front-loaded with the purpose. However, it could be more informative without sacrificing 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?

Given the tool's simple input (one required parameter), the description is adequate but lacks context. There is no output schema, and the description does not state what the tool returns. For a tool with siblings, more differentiation is needed for completeness.

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%, but there is only one parameter (team_id) with no description in the schema. The description does not explain what team_id represents or provide any guidance on its value. Baseline 3 is used because the schema is simple and only one parameter exists, but the description adds no value.

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 the tool gets the team's annual goals (チームの年間目標を取得する). While the verb '取得する' (get) and resource '年間目標' (annual goals) are clear, the description does not differentiate from sibling tools like get_goals which may return a different scope of goals.

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_goals. There is no mention of prerequisites or context for using the tool, leaving the agent to infer its usage from the name alone.

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