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 effectively describes the tool's behavior: it performs bidirectional conversion, returns both millisecond and second timestamps, supports multiple time formats, and has a default timezone. However, it doesn't mention error handling, rate limits, or authentication requirements, which keeps it from a perfect score.

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 clear sections (功能, 参数说明, 使用示例, 返回格式) and uses bullet points effectively. While comprehensive, it could be slightly more concise by integrating some of the usage examples into the functional description rather than having a separate section.

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 complexity (bidirectional conversion with multiple parameter formats) and the presence of an output schema, the description is complete. It explains what the tool does, how to use it, parameter details, practical examples, and what to expect in the return values, making it fully self-contained despite the lack of annotations and schema descriptions.

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, the description fully compensates by providing detailed parameter semantics. It explains that timestamp and human_readable are mutually exclusive parameters, documents the exact formats supported for human_readable (absolute time, relative time, combinations, offsets), and clarifies the purpose of the timezone parameter with its default 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 clearly states the tool's purpose as a time and timestamp conversion utility for CLS tools, specifying it converts between human-readable time and Unix timestamps. It distinguishes itself from sibling tools by explicitly mentioning its role in preparing parameters for tools like cls_search_log and cls_query_metric, which none of the other tools do.

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 on when to use this tool ('before calling CLS tools that require timestamp parameters') and includes practical examples showing how to use it for specific scenarios like querying yesterday's data or recent time ranges. It also mentions which sibling tools benefit from its output (cls_search_log for milliseconds, cls_query_metric for seconds).

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 describes what information is returned (e.g., configuration, notification channels, associated topics) but lacks behavioral details such as error handling, permissions required, rate limits, or whether it's a read-only operation. The description doesn't contradict annotations (none exist), but it's insufficient for a mutation-sensitive 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 well-structured with a clear purpose statement, parameter explanations in a bulleted list, and return information details. It's appropriately sized—every sentence adds value, such as clarifying parameter usage and output content. Minor room for improvement in flow, but it's efficient and 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?

Given the tool has an output schema (implied by 'Has output schema: true'), the description doesn't need to detail return values, and it appropriately summarizes them. With no annotations and 0% schema coverage, the description compensates well by explaining parameters and purpose. It's complete enough for a read operation, though more behavioral context would enhance it.

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 fully. It provides detailed semantics for both parameters: 'alarm_id' is required and explained as the alarm policy ID, and 'region' is optional with examples (ap-guangzhou, na-ashburn), default behavior (uses default if not provided), and a reference to another tool for querying regions. This adds significant value 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's purpose: '获取告警策略详情' (get alarm policy details) and specifies it retrieves complete alarm configuration information based on an alarm ID. It distinguishes from siblings like 'cls_describe_alarms' (likely lists alarms) and 'cls_get_alarm_detail' (similar but not identical naming), though the distinction isn't explicitly stated. The verb '获取' (get) and resource '告警策略详情' (alarm policy details) are specific.

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 when needing full alarm configuration details for a specific alarm ID, as opposed to listing alarms or other alarm-related operations. It mentions an alternative tool 'cls_describe_regions' for querying available regions, but doesn't explicitly state when to use this tool versus siblings like 'cls_describe_alarms' or 'cls_get_alarm_detail'. Guidelines are present but not comprehensive.

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 states this is a query/list operation, implying it's likely read-only and non-destructive, but doesn't explicitly confirm safety aspects like permissions required, rate limits, or whether it modifies data. The description adds some context about default region behavior and references another tool for region info, but lacks details on response format, pagination behavior beyond offset/limit, or error conditions.

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 clear purpose statement followed by a parameter section. It's front-loaded with the main functionality. Sentences are efficient: the first sentence states the action and resource, the second elaborates on what's retrieved. The parameter explanations are brief but informative. Minor improvements could include merging the two initial sentences or adding bullet points for clarity, but overall it's concise with minimal waste.

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 an output schema (which handles return values), 4 parameters with 0% schema coverage but good description compensation, and no annotations, the description is reasonably complete. It covers purpose, parameters with semantics, and hints at usage context. It could be more complete by explicitly stating behavioral traits (e.g., read-only, pagination details) and differentiating from siblings, but for a query tool with output schema, it provides adequate context for basic use.

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 provides a parameter section explaining all 4 parameters: offset (pagination offset, default 0), limit (items per page, default 20), name (filter by notification name, optional), and region (region like ap-guangzhou, optional, defaults to default region). This adds meaningful semantics beyond the schema's basic titles and types, covering defaults, optionality, and examples. However, it doesn't detail format constraints (e.g., region string patterns) or interactions between parameters.

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: '查询告警通知渠道列表' (query alarm notification channel list) and '获取当前账号配置的告警通知方式' (get the current account's configured alarm notification methods). It specifies the resource (alarm notification channels/methods) and action (query/list/get). However, it doesn't explicitly differentiate from sibling tools like cls_describe_alarms or cls_describe_alarm_records, which also deal with alarms but focus on different aspects.

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 context by mentioning it retrieves notification methods for alarms, suggesting it should be used when needing to know how alarms are delivered. It provides one explicit alternative: '可通过 cls_describe_regions 查询所有可用地域' (can use cls_describe_regions to query all available regions) for the region parameter. However, it lacks broader guidance on when to use this tool versus other alarm-related siblings like cls_describe_alarms, and doesn't specify prerequisites 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 full burden and adds valuable behavioral context. It explains pagination behavior (offset/limit defaults), time format requirements (Unix timestamp in milliseconds), region handling (optional with default), and references other tools for conversions. However, it doesn't mention rate limits, authentication needs, or whether this is a read-only operation (though implied by '查询').

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?

Well-structured with clear sections (description, parameter说明, 适用场景, 注意事项), each sentence adds value. The description is appropriately sized for a 9-parameter tool with no schema documentation, front-loading the core purpose while organizing details logically. No wasted 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?

Given the complexity (9 parameters, 0% schema coverage, no annotations) and presence of an output schema (which handles return values), the description is remarkably complete. It covers purpose, parameters, usage scenarios, prerequisites (time conversion tool), and regional considerations. The only minor gap is lack of explicit read/write classification, but the output schema likely addresses response format.

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

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

Schema description coverage is 0%, so the description fully compensates with detailed parameter documentation. The '参数说明' section explains all 9 parameters with clear semantics: required vs optional, data types (Unix timestamps, integers, strings), defaults, filtering purposes, and enum mappings for status (0-2) and alarm_level (0-2). It adds crucial context 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's purpose: '查询告警历史记录' (query alarm history records) with specific details about viewing recent alarm triggers, time, cause, and status. It distinguishes from siblings like cls_describe_alarms (likely for alarm policies) and cls_describe_alarm_detail (likely for single alarm details), but doesn't explicitly name these alternatives. The purpose is clear but lacks explicit 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 '适用场景' (applicable scenarios) section provides explicit guidance on when to use this tool: for investigating alarm policy history, viewing all alarm records for a log topic, filtering by status/level, and understanding recent alarm trends. It also references sibling tools (cls_describe_topics, cls_convert_time, cls_describe_regions) for related operations, offering clear alternatives and prerequisites.

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 effectively discloses key behavioral traits: it's a read operation (implied by '查询'), supports pagination (offset/limit with defaults and max limit), filtering options (name, topic_id, region), and default region behavior. It also hints at authentication context ('当前账号下') and mentions the response format. However, it doesn't cover rate limits, error conditions, or exact permission 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 well-structured with a clear purpose statement followed by organized sections for parameters and return information. Every sentence adds value: the opening defines scope, parameter details are essential for understanding, and return info clarifies output. It could be slightly more front-loaded by moving key behavioral notes (e.g., pagination defaults) earlier, but overall it's efficient and informative.

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 moderate complexity (5 parameters, filtering, pagination), no annotations, but with an output schema (implied by '返回信息'), the description is quite complete. It covers purpose, usage context, parameter semantics, and output structure. The output schema existence means the description doesn't need to detail return values exhaustively. Minor gaps include lack of error handling or authentication specifics, but it's sufficient for effective use.

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 fully compensate. It does this excellently by providing detailed parameter semantics in the '参数说明' section: explaining each parameter's purpose (e.g., offset for pagination, limit with max value, name for fuzzy matching), optionality, defaults, and practical usage notes (e.g., using cls_describe_topics if topic_id is unknown). This adds significant value 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's purpose as '查询告警策略列表' (query alarm policy list) and specifies it retrieves alarm policy information for the current account. It distinguishes from siblings like cls_describe_alarm_detail (detail view) and cls_describe_alarm_records (records) by focusing on listing policies with filtering capabilities. However, it doesn't explicitly contrast with all similar tools like cls_get_alarm_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 clear context for when to use this tool: to list alarm policies with pagination and filtering. It offers guidance on alternatives for related tasks, such as using cls_describe_topics to search by name if topic_id is uncertain, and cls_describe_regions to query available regions. However, it doesn't explicitly state when NOT to use it (e.g., vs. cls_describe_alarm_detail for detailed info).

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 mentions pagination (offset/limit) and optional filtering, but doesn't disclose critical behavioral traits: whether this is a read-only operation, potential rate limits, authentication requirements, error conditions, or what happens if no dashboards exist. For a list tool with zero annotation coverage, this leaves significant 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 well-structured and appropriately sized. It starts with a clear purpose statement, followed by a parameter section with bullet points. Every sentence earns its place, though it could be slightly more front-loaded by integrating parameter hints into the initial summary. No wasted 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?

Given the tool's moderate complexity (list operation with filtering/pagination), no annotations, but with an output schema (which handles return values), the description is fairly complete. It covers all parameters thoroughly and references related tools. However, it lacks behavioral context (e.g., safety, limits), which is a minor gap since the output schema exists.

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 description coverage is 0%, so the description must compensate fully. It does so excellently: it explains all 4 parameters with clear semantics—offset as pagination offset, limit as items per page, dashboard_name for filtering, and region with examples and a reference to another tool for valid values. This adds substantial 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 clearly states the tool's purpose: '查询仪表盘列表。获取当前账号下的 CLS 仪表盘。' (Query dashboard list. Get CLS dashboards under the current account.) This specifies the verb ('query/list') and resource ('CLS dashboards'), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'cls_describe_regions' or 'cls_describe_topics', which describe other 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 some implied usage context: it mentions filtering by dashboard name and region, and references 'cls_describe_regions' for available regions. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., no comparison to other 'describe' tools for dashboards or search functions). The context is clear but not comprehensive.

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 full burden. It describes what the tool returns (task list with IDs, names, statuses, source/destination topics, processing statements, creation times) and mentions pagination behavior through offset/limit parameters. However, it doesn't disclose important behavioral traits like whether this is a read-only operation (implied but not stated), rate limits, authentication requirements, or error conditions. The description adds useful context about what 'data processing' means but lacks comprehensive behavioral disclosure.

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 clear sections: purpose statement, parameter explanations, and return information. Each sentence earns its place by providing necessary information. The front-loaded purpose statement is clear, though the Chinese formatting with markdown headers might be slightly less accessible than plain text. It's appropriately sized for a tool with 5 parameters and detailed return expectations.

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 complexity (5 parameters, no annotations, but has output schema), the description provides good coverage. It explains all parameters thoroughly, describes what the tool returns, and provides context about data processing. The existence of an output schema means the description doesn't need to exhaustively document return values. However, it could better address when to use this versus similar tools and provide more behavioral context given the lack of annotations.

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 (titles only provide parameter names without meaning), the description fully compensates by explaining all 5 parameters in detail. It provides: 1) offset as pagination offset with default 0, 2) limit as items per page with default 20, 3) task_name as optional filter by task name, 4) topic_id as optional filter by source log topic ID with guidance on how to find IDs, 5) region as optional region parameter with examples and guidance on how to query available regions. This adds significant value 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's purpose: '查询数据加工任务列表' (query data processing task list) with specific context about what data processing entails ('数据加工用于对日志数据进行清洗、转换、分发等处理' - data processing is used for cleaning, transforming, and distributing log data). It distinguishes itself from siblings like cls_describe_topics by focusing specifically on data transform tasks rather than general topics or other 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 clear context for when to use certain parameters (e.g., '如不确定 ID，可先通过 cls_describe_topics 按名称搜索' - if unsure about ID, first search by name using cls_describe_topics; '可通过 cls_describe_regions 查询所有可用地域' - can query all available regions using cls_describe_regions). However, it doesn't explicitly state when to use this tool versus alternatives like cls_describe_scheduled_sql_tasks or other describe_* siblings, missing explicit comparison 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by explaining what information is returned (full-text index configuration, key-value index configuration, index status), which helps the agent understand the output. However, it doesn't mention important behavioral aspects like whether this is a read-only operation (implied but not stated), error conditions, rate limits, or authentication 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 well-structured with clear sections (purpose, parameter explanation, return information). It's appropriately sized - every sentence adds value. The only minor issue is some redundancy between the opening statement and the parameter/return sections, but overall it's efficient and front-loaded with the core purpose.

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 there's an output schema (which handles return values), no annotations, and good parameter coverage in the description, this description is complete enough. It explains the purpose, parameters, and what information will be returned at a high level. The output schema will provide the detailed structure, so the description doesn't need to duplicate that information.

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 description coverage is 0%, so the description must fully compensate. It provides excellent parameter semantics: clearly explains topic_id is required and what it represents, explains region is optional with examples of valid values (ap-guangzhou, na-ashburn), describes the default behavior when region is not provided, and references another tool (cls_describe_regions) for getting all available regions. This adds substantial value 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's purpose as '查询日志主题的索引配置' (query log topic index configuration), specifying both the verb (query) and resource (log topic index configuration). It distinguishes from siblings like cls_describe_topic_detail (which likely describes general topic details) and cls_describe_regions (which lists regions) by focusing specifically on index configuration.

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 for when to use this tool: to query index configuration for log topics. It mentions an alternative tool (cls_describe_regions) for getting available regions, which helps differentiate usage. However, it doesn't explicitly state when NOT to use this tool or compare it to other similar describe tools like cls_describe_topic_detail.

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 full burden. It describes the tool as a query operation (consistent with read-only behavior) and mentions pagination behavior (offset/limit defaults). However, it doesn't disclose important behavioral traits like authentication requirements, rate limits, error conditions, or whether this is a safe read operation versus a mutation.

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 clear sections (purpose, parameters, return information). Every sentence earns its place by providing essential information. The Chinese text is efficient with no redundant phrases. The structure helps users quickly find what they need.

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 an output schema (true), the description appropriately focuses on explaining what the tool does rather than detailing return values. It covers parameters comprehensively and provides context about logsets. For a read-only list tool, this is mostly complete, though it could benefit from more behavioral context given the lack of annotations.

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, the description fully compensates by providing detailed parameter explanations. Each of the 4 parameters gets clear semantic meaning: offset as pagination offset, limit as page size, logset_name as fuzzy match filter, and region with examples and reference to another tool. The description adds significant value 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's purpose with specific verb ('查询' - query) and resource ('日志集列表' - logsets list). It distinguishes from siblings by focusing on logsets rather than topics, alarms, or other CLS resources. The explanation that logsets are project management units containing multiple log topics provides helpful context.

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 for when to use this tool (to list logsets with optional filtering). It mentions that region can be obtained via 'cls_describe_regions', which is a helpful alternative reference. However, it doesn't explicitly state when NOT to use this tool or compare it directly with similar sibling tools like 'cls_describe_topics'.

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 describes what information is retrieved (configuration and online status) but lacks behavioral details such as whether this is a read-only operation, potential rate limits, authentication requirements, error conditions, or response format. The description doesn't contradict annotations (none exist), but provides minimal 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 appropriately sized with two clear sections: a purpose statement followed by parameter explanations. Every sentence adds value, though the structure could be slightly more front-loaded by integrating parameter hints into the main description. No wasted 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?

Given the tool has an output schema (which handles return values), 2 parameters with good semantic coverage in the description, and no annotations, the description is reasonably complete. It covers purpose, usage context, and parameter meanings adequately, though more behavioral transparency would improve completeness for a tool with no annotations.

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, the description compensates well by explaining both parameters: 'group_id' is required and identifies the machine group, and 'region' is optional with examples (ap-guangzhou, na-ashburn), default behavior (uses default if not provided), and how to find available values (via cls_describe_regions). This adds 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 clearly states the specific action ('获取机器组详情和机器状态' - get machine group details and machine status) and resource ('机器组' - machine group). It distinguishes from sibling tools like 'cls_describe_machine_groups' (which likely lists groups) by focusing on details and status of a specific group.

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 for when to use this tool: to view configuration information and online status of machines within a group. It mentions an alternative tool ('cls_describe_regions') for querying available regions, but doesn't explicitly state when NOT to use this tool or compare it to all relevant siblings like 'cls_describe_machine_groups'.

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. While it mentions this is a query/list operation, it doesn't disclose important behavioral traits like whether this requires authentication, rate limits, pagination behavior beyond basic offset/limit parameters, or what happens when no results match filters. The description provides some context about machine groups but lacks operational 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 well-structured with a clear purpose statement followed by organized parameter explanations. Every sentence earns its place by providing essential information. It could be slightly more front-loaded with a clearer distinction from sibling tools, but overall it's appropriately sized and efficiently organized.

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 an output schema (which handles return values), 4 parameters with good description coverage, and moderate complexity, the description is reasonably complete. It explains what machine groups are, documents all parameters with semantics, and references related tools. The main gap is lack of behavioral transparency around authentication, rate limits, and error conditions.

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 provides excellent parameter semantics beyond the input schema. With 0% schema description coverage, the description fully compensates by explaining all 4 parameters: offset (pagination offset, default 0), limit (items per page, default 20), group_name (filter by machine group name, optional), and region (geographic region, optional, with examples and reference to another tool for available regions). This adds significant value 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 purpose as '查询机器组列表' (query machine group list), which is a specific verb+resource combination. It further explains that machine groups are management units for log collection endpoints. However, it doesn't explicitly differentiate from sibling tools like 'cls_describe_machine_group_detail' which presumably provides detailed information about a specific machine group.

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 some implied usage context by mentioning that machine groups are '用于统一管理一组日志源机器' (used to uniformly manage a group of log source machines). It also references 'cls_describe_regions' for getting available regions. However, it doesn't explicitly state when to use this tool versus alternatives like 'cls_describe_machine_group_detail' or provide clear 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 full burden. It effectively describes the tool's behavior: it's a read-only query (implied by '查询'), returns specific data fields (region IDs and Chinese names), and has no parameters. It doesn't mention rate limits, authentication needs, or pagination, but for a simple metadata query tool, the description provides adequate 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 well-structured with clear sections (### 无需参数, ### 返回信息, ### 使用场景), front-loads the core purpose, and every sentence adds value. No redundant information or 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's simplicity (0 parameters, read-only query, has output schema), the description is complete. It explains what the tool does, when to use it, what it returns, and that no parameters are needed. The output schema will handle return value documentation, so the description appropriately focuses on usage 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?

The tool has 0 parameters with 100% schema description coverage. The description explicitly states '无需参数' (no parameters needed) and '直接调用即可' (call directly), which adds helpful confirmation beyond the empty schema. This exceeds the baseline expectation for parameterless tools.

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 as '查询 CLS 支持的地域列表' (query CLS supported region list), specifying both the verb (query) and resource (region list). It distinguishes itself from siblings by focusing on region metadata rather than logs, alarms, dashboards, or other CLS resources mentioned in sibling tool names.

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 provides usage scenarios: '不确定某个城市/地区对应的地域 ID 时，先调用此工具查询' (when unsure about region ID for a city/area, call this tool first) and '需要列出所有可用地域供用户选择时使用' (use when needing to list all available regions for user selection). This gives clear when-to-use guidance with practical 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 provided, the description carries the full burden. It describes the tool as a query/list operation (implied read-only) and provides some behavioral context about pagination defaults and regional behavior. However, it doesn't disclose important traits like rate limits, authentication requirements, error conditions, or whether the operation is idempotent.

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 clear sections for purpose, parameters, and return information. It's appropriately sized with no wasted sentences. The only minor issue is that the purpose statement could be more front-loaded before the detailed sections.

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 moderate complexity (5 parameters, no annotations, but has output schema), the description provides good coverage. The output schema exists, so the description doesn't need to explain return values in detail (though it helpfully summarizes them). The main gap is lack of behavioral context that annotations would normally provide.

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, the description fully compensates by providing detailed parameter explanations in Chinese. Each of the 5 parameters gets clear semantic meaning, including defaults, optionality, examples (region values), and references to other tools. This adds significant value 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's purpose as '查询定时 SQL 任务列表' (query scheduled SQL task list) and explains that these tasks are for periodic SQL analysis with results stored in target log topics. This provides a specific verb+resource combination, though it doesn't explicitly differentiate from sibling tools like cls_describe_data_transform_tasks or cls_describe_topics.

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 context through the parameter explanations (e.g., region defaults and reference to cls_describe_regions for available regions) but doesn't provide explicit guidance on when to use this tool versus alternatives. No when-not-to-use or sibling tool comparisons are included.

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 discloses key behavioral traits: it returns a complete syntax reference document, lists specific content included (e.g., CQL retrieval syntax, SQL analysis syntax, CLS extension functions), and states '调用此工具不需要任何参数' (no parameters needed for calling this tool). However, it doesn't mention response format, size, or potential rate limits, leaving some behavioral aspects unspecified.

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 and appropriately sized. It starts with a clear purpose and usage guideline, followed by a bulleted list of content included, and ends with the parameter note. Every sentence earns its place by providing essential information without redundancy, making it easy to scan and understand.

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 complexity (providing syntax documentation), the description is complete. It details what the tool returns (a comprehensive reference with specific sections), when to use it, and that no parameters are needed. With an output schema present (as indicated by context signals), the description doesn't need to explain return values, and it adequately covers all necessary contextual aspects for a zero-parameter documentation 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 0 parameters, with schema description coverage at 100%. The description explicitly states '调用此工具不需要任何参数' (no parameters needed), which adds clarity beyond the empty schema. Since there are no parameters, the baseline is 4, and the description confirms this effectively.

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's purpose: '返回 CLS CQL 完整语法参考文档' (returns the complete CLS CQL syntax reference documentation). It distinguishes itself from sibling tools by specifying it's for CQL search syntax documentation, unlike cls_search_log (which executes queries) or other describe tools focused on alarms, dashboards, etc. The verb '返回' (return) and resource '参考文档' (reference documentation) are specific and clear.

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 on when to use this tool: '当 cls_search_log 执行报错或不确定如何编写查询语句时使用' (use when cls_search_log execution errors or unsure how to write query statements). It names the alternative tool (cls_search_log) and specifies the context (error or uncertainty in query writing), offering clear when-to-use criteria that differentiate it from siblings.

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 describes a read-only operation ('获取' - get, '查看' - view) without implying mutation, which is appropriate. However, it doesn't disclose behavioral traits such as authentication needs, rate limits, error handling, or what '完整配置信息' includes. The description adds basic context but misses key operational details that would help an agent use it correctly.

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 clear purpose statement followed by a parameter section. It uses bullet points for parameters, making it easy to scan. Every sentence adds value: the first states the purpose, and the parameter explanations provide necessary context. It could be slightly more concise by integrating the parameter details more seamlessly, but overall it's efficient and 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?

Given the context: 2 parameters, 0% schema coverage, no annotations, but an output schema exists. The description covers the purpose and parameters well, and since an output schema is present, it doesn't need to explain return values. It's complete enough for a read operation, though it could benefit from more behavioral transparency (e.g., error cases) to fully guide the 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 schema description coverage is 0%, so the description must compensate. It provides a parameter section explaining 'topic_id' as required and 'region' as optional with examples (e.g., 'ap-guangzhou') and references 'cls_describe_regions' for available values. This adds meaningful semantics beyond the bare schema, covering both parameters adequately. However, it doesn't detail format constraints or validation rules, keeping it from a perfect score.

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: '获取日志主题详情。查看日志主题的完整配置信息' (Get log topic details. View complete configuration information for a log topic). It specifies the verb ('获取' - get) and resource ('日志主题详情' - log topic details), making it easy to understand. However, it doesn't explicitly differentiate from sibling tools like 'cls_describe_topics' which might list topics rather than get details of a specific one.

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 by specifying that it retrieves '完整配置信息' (complete configuration information), suggesting it's for detailed views rather than summaries. It mentions an alternative tool 'cls_describe_regions' for querying available regions, but doesn't provide explicit guidance on when to use this tool versus other siblings like 'cls_describe_topics' or 'cls_describe_logsets'. The context is clear but lacks comprehensive alternatives 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 of behavioral disclosure. It effectively describes the tool's behavior as a read-only query operation (implied by '查询'), includes pagination details (offset/limit defaults), filtering options, and region handling. It also outlines the return information structure, though it doesn't cover aspects like error conditions, rate limits, or authentication needs, which keeps it from a perfect score.

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 clear sections (purpose, parameter explanations, return info) and uses bullet points for readability. It is appropriately sized, though the parameter section is lengthy due to covering all parameters—this is necessary given the lack of schema descriptions, so it earns its place without being wasteful.

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 query tool with 6 parameters, 0% schema coverage, no annotations, but an output schema, the description is quite complete. It explains the tool's purpose, all parameters in detail, and the return information. The output schema likely covers return values, so the description doesn't need to duplicate that. Minor gaps include lack of error handling or explicit sibling tool comparisons, but overall it provides sufficient context for effective use.

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?

Given 0% schema description coverage, the description fully compensates by providing detailed semantic explanations for all 6 parameters. It clarifies defaults (e.g., offset=0, limit=20), optionality, filtering logic (e.g., fuzzy matching for topic_name), enum values for biz_type (0 for log topics, 1 for metric topics), and region usage with a reference to another tool. This adds significant value 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's purpose as '查询日志主题列表' (query log topic list) and explains that log topics are basic storage units for log data. This provides a specific verb ('query') and resource ('log topic list'), though it doesn't explicitly differentiate from sibling tools like 'cls_describe_logsets' or 'cls_describe_topic_detail' beyond the resource type.

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 some implied usage guidance through parameter explanations (e.g., '当需要查询指标主题时，请传入 biz_type=1' for querying metric topics, and mentioning 'cls_describe_regions' for available regions). However, it lacks explicit when-to-use vs. alternatives (e.g., compared to 'cls_describe_topic_detail' for detailed info) or prerequisites, leaving room for improvement.

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 effectively describes key behaviors: the tool automatically parses URLs and returns formatted Markdown, supports both short and long URL formats, short links automatically redirect to long links for parsing, and it's a '免密接口' (password-free interface) requiring no additional authentication. However, it doesn't mention rate limits, error handling, or performance characteristics.

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 clear sections (query methods, parameter explanation, URL formats, return content, application scenarios, notes) but could be more concise. Some information is repeated (e.g., the mutual exclusivity rule appears in multiple sections), and the Markdown formatting adds visual clarity but also length. Most sentences earn their place by providing distinct value.

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 complexity (3 parameters with mutual exclusivity rules, multiple input formats, rich output) and the presence of an output schema, the description is remarkably complete. It covers all input methods, parameter semantics, URL formats, detailed return content structure, application scenarios, and important behavioral notes. The output schema existence means the description doesn't need to explain return values in technical 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?

With 0% schema description coverage (titles only provide parameter names), the description fully compensates by providing comprehensive parameter semantics. It explains that 'url' accepts both short and long link formats, 'record_id' comes from cls_describe_alarm_records results, and 'region' is a geographic identifier with examples like 'ap-guangzhou'. It also clarifies the mutual exclusivity rule between parameter groups.

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: '通过告警详情URL获取CLS告警的详细信息' (get detailed information about CLS alarms through alarm detail URLs). It specifies the verb ('获取' - get/retrieve) and resource ('CLS告警的详细信息' - CLS alarm details), and distinguishes from siblings like cls_describe_alarm_records (which lists alarms) by focusing on retrieving detailed information for specific alarms.

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 on when to use this tool vs alternatives. It outlines two query methods (URL-based vs record_id+region), explains that record_id and region can be obtained from cls_describe_alarm_records, and specifies application scenarios including '快速查看告警详情' (quickly view alarm details) and '从告警记录列表查看详情' (view details from alarm record list). It also explicitly states 'url 与 record_id+region 二选一' (choose one between url and record_id+region).

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 effectively describes key behaviors: it's a read operation (获取/查看 - get/view), specifies constraints (prev_logs/next_logs defaults and maximums of 10/100), explains timezone handling (UTC+8 conversion for timestamps, must use UTC+8 for strings), mentions accuracy considerations (millisecond precision affects accuracy), and notes optional parameters with defaults. It doesn't cover rate limits or authentication needs, but provides substantial operational 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 well-structured with clear sections (purpose, parameter说明, 使用流程, 注意事项) and front-loaded purpose. It's appropriately sized for a 7-parameter tool with complex usage. Some sentences could be slightly tightened (e.g., the region note is a bit verbose), but overall it's efficient with minimal waste.

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 complexity (7 parameters, 4 required, no schema descriptions, no annotations) and the presence of an output schema (which handles return values), the description is highly complete. It covers purpose, detailed parameter semantics, usage workflow, prerequisites, alternatives, constraints, and operational notes. The only minor gap is lack of explicit authentication/rate limit info, but this is compensated by the comprehensive parameter and usage guidance.

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 fully compensate. It provides detailed semantic information for all 7 parameters: explains required vs. optional, sources for values (e.g., from cls_search_log results), formats (two time string formats, integer IDs), defaults (prev_logs=10, next_logs=10, region=''), constraints (max 100), and practical usage notes (timezone handling, precision advice). This goes well beyond what the bare schema titles offer.

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: '获取日志上下文。根据一条日志的定位信息，查看其前后的日志记录，用于排查问题时了解完整的日志上下文' (Get log context. Based on a log's positioning information, view logs before and after it, used to understand the complete log context when troubleshooting problems). This is specific (verb: get/view, resource: log context), distinguishes it from siblings like cls_search_log (which finds logs) and cls_get_log_count (which counts logs), and explains the value (troubleshooting).

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 on when and how to use this tool versus alternatives. It specifies a clear workflow: '1. 先用 cls_search_log 查找目标日志 2. 从结果中获取... 3. 用这些信息调用本工具' (1. First use cls_search_log to find the target log 2. Get... from the results 3. Use this information to call this tool). It also mentions an alternative tool for region queries (cls_describe_regions) and clarifies that region is optional with a default.

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 full burden and does well. It discloses important behavioral traits: performance characteristics (faster than cls_search_log), prerequisite tools (cls_convert_time for timestamp conversion, cls_describe_index for SQL preparation), and error handling guidance for topic_id. It doesn't mention rate limits or authentication needs, but covers substantial operational 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 well-structured with clear sections (参数说明, 适用场景, 注意事项) and uses emphasis (⏰, 💡) effectively. While comprehensive, it maintains focus with each sentence adding value. Some redundancy exists in parameter explanations, but overall it's efficiently organized.

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 complexity (5 parameters, 0% schema coverage, no annotations) and presence of output schema, the description is remarkably complete. It covers purpose, usage guidelines, parameter details, prerequisite tools, error handling, and operational constraints. The output schema existence means return values don't need explanation, allowing focus on invocation 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?

With 0% schema description coverage, the description fully compensates by providing rich parameter semantics. It explains each parameter's purpose, format constraints (UUID or custom string for topic_id, Unix timestamp in milliseconds for time fields), optionality, and practical usage guidance including fallback strategies for topic_id resolution and region defaults.

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: '快速获取日志数量' (quickly get log count). It distinguishes from sibling cls_search_log by noting it's faster and suitable for scenarios where only the total count is needed. This provides specific verb+resource and 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 explicitly states when to use this tool ('适合只需要知道日志总数的场景' - suitable for scenarios where only total count is needed) and when to use alternatives ('相比 cls_search_log 更快' - faster than cls_search_log). It also provides specific usage scenarios like confirming log existence and counting logs in time ranges.

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 discloses important behavioral traits: the tool is for statistical analysis (not destructive), requires specific time format handling (millisecond Unix timestamps), and suggests prerequisites like calling cls_convert_time for time conversion and cls_describe_index for field validation. However, it doesn't mention rate limits, authentication needs, or pagination behavior, leaving some 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 well-structured with clear sections (purpose, parameters, scenarios, notes) and uses bullet points for readability. It's appropriately sized but could be slightly more concise in the notes section. Every sentence adds value, such as the warning about time conversion and suggestions for related tools.

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 (6 parameters, no annotations, but has output schema), the description is mostly complete. It covers purpose, parameters, usage scenarios, and prerequisites. Since an output schema exists, it doesn't need to explain return values. However, it lacks details on error handling or performance considerations, which could be useful for a tool with multiple parameters and dependencies.

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, the description fully compensates by providing detailed parameter semantics in the '参数说明' (Parameter explanation) section. It explains each parameter's purpose, required status, format (e.g., 'CQL 检索语句' - CQL query statement, Unix timestamp in milliseconds), and practical examples (e.g., query: 'level:ERROR' or '*'). This adds significant value 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's purpose: '获取日志数量直方图。统计指定时间范围内日志在时间维度上的分布情况，用于观察日志量趋势和异常波动' (Get log count histogram. Count log distribution across time within a specified range, used to observe log volume trends and abnormal fluctuations). It specifies the verb ('获取' - get), resource ('日志数量直方图' - log count histogram), and distinguishes it from siblings like cls_search_log (for detailed logs) and cls_get_log_count (for total count).

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 provides usage guidelines in the '适用场景' (Applicable scenarios) section: observing log volume trends over time, detecting sudden increases or decreases, and combining with cls_search_log to locate specific abnormal periods. It also mentions when not to use it (e.g., for detailed logs, use cls_search_log instead). This gives clear context for when to choose this tool over 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the tool returns metric names that have data within the specified time range, recommends querying the last 15 minutes for practical use, and warns about time format requirements (seconds, not milliseconds). However, it doesn't mention pagination, rate limits, or authentication 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 well-structured with clear sections (purpose, parameters, usage scenarios, notes), front-loaded with the core purpose, and every sentence adds value. The bullet points make it scannable, and there's no redundant information. The warning about time conversion is appropriately emphasized with emoji and bold formatting.

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 an output schema (which handles return values), no annotations, and 4 parameters with 0% schema coverage, the description provides excellent contextual completeness. It covers purpose, parameters, usage guidelines, behavioral constraints, and references to related tools. The time format warning and practical recommendation (query last 15 minutes) add important operational 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?

With 0% schema description coverage, the description fully compensates by providing detailed parameter semantics in the '参数说明' section. It explains each parameter's purpose, requirements (必填 for required), format constraints (Unix timestamp in seconds), default behavior (region defaults if not provided), and provides examples (ap-guangzhou, na-ashburn). The warning about time conversion is particularly 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's purpose with specific verbs ('列出' meaning 'list') and resources ('指标名称' meaning 'metric names'), and distinguishes it from siblings by explaining it's used before querying metrics with cls_query_metric/cls_query_range_metric. It explicitly differentiates from logging topics by specifying '时序指标主题 ID, 非普通日志主题 ID'.

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 usage guidelines in the '使用场景' section, stating when to use this tool (before querying metrics with cls_query_metric/cls_query_range_metric, to understand available metrics) and when not to use it (not for logging topics). It also mentions an alternative tool (cls_convert_time for time conversion) and references cls_describe_regions for region 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the tool queries metric data (not logs), supports PromQL-compatible syntax, returns values at a specific time point, and has region-specific behavior. It also provides important operational guidance about time conversion. The only minor gap is lack of explicit mention about authentication or rate limits.

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 clear sections (purpose, parameters, examples, notes) and efficiently conveys necessary information. Every sentence adds value, though the PromQL examples section could be slightly more concise. The structure is front-loaded with the core purpose, followed by detailed supporting 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?

Given the tool's complexity (metric querying with PromQL), 0% schema coverage, no annotations, but with an output schema present, the description provides excellent completeness. It covers purpose, parameters with semantics, usage examples, important operational notes, and references to related tools. The output schema existence means the description doesn't need to explain return values, allowing it to focus on usage 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?

With 0% schema description coverage, the description fully compensates by providing comprehensive parameter semantics. It explains all four parameters in detail: topic_id (required metric topic ID, not log topic), query (required PromQL syntax), time (optional Unix timestamp in seconds, default current time), and region (optional, with examples). It also provides PromQL examples that clarify the query parameter usage beyond basic schema information.

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: '查询 CLS 指标数据（单时间点）' (query CLS metric data at a single time point). It specifies the verb '查询' (query) and resource 'CLS 指标数据' (CLS metric data), and distinguishes it from sibling tools like cls_query_range_metric by emphasizing '单时间点' (single time point). This provides specific differentiation from 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?

The description provides explicit usage guidance. It states when to use this tool (for single-time-point metric queries with PromQL syntax) and when not to (implied by distinguishing from range queries). It also names alternatives: cls_convert_time for time conversion and cls_describe_regions for region lookup, creating clear contextual boundaries.

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 effectively describes key behaviors: it supports PromQL-compatible query syntax, returns metric trends over time, requires specific topic_id format (time-series metric topic ID, not log topic ID), and has region defaults. It also mentions error handling for topic_id. However, it doesn't cover rate limits, authentication needs, or pagination behavior, leaving some 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 well-structured with clear sections (purpose, parameters, scenarios, notes). It's appropriately sized for a 6-parameter tool with no annotations. Every sentence adds value, though the parameter section is detailed, which is necessary given the 0% schema coverage. It could be slightly more front-loaded by moving the purpose statement to the very beginning.

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 (6 parameters, 0% schema coverage, no annotations, but with output schema), the description is remarkably complete. It covers purpose, all parameters with semantics, usage scenarios, critical notes, and references to sibling tools. The presence of an output schema means the description doesn't need to explain return values. This provides everything needed for effective tool selection and invocation.

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 description coverage is 0%, so the description must fully compensate. It provides detailed parameter semantics in the '参数说明' section, explaining each of the 6 parameters with purpose, format, requirements, defaults, and practical usage notes (e.g., topic_id format ambiguity resolution, time conversion requirement). This adds substantial value 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's purpose: '查询 CLS 指标数据（时间范围）' (query CLS metric data with time range). It specifies the verb (query), resource (CLS metric data), and scope (time range). It distinguishes from sibling tools like cls_query_metric (which likely doesn't have time range) and cls_search_log (which handles logs not metrics).

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 usage guidance in the '适用场景' (applicable scenarios) section, listing three specific use cases. It also includes '注意事项' (notes) with critical instructions about time conversion, explicitly naming the alternative tool cls_convert_time. This gives clear when-to-use and when-not-to-use 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?

With no annotations provided, the description carries full burden and does an excellent job disclosing behavioral traits: it explains the CQL/SQL syntax, default return limits (100 rows, max 1M for SQL), pagination via context parameter, timezone handling (UTC+8 vs UTC+0), error handling recommendations, and regional defaults. The only minor gap is lack of explicit rate limit or authentication 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 comprehensive but overly long (500+ words) with extensive syntax documentation that might be better in separate reference tools. While well-structured with clear sections, it includes implementation details like CQL syntax examples and SQL function references that exceed what's needed for tool selection. Some content could be moved to cls_describe_search_syntax.

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 complexity (8 parameters, no annotations, rich functionality) and presence of an output schema, the description is remarkably complete. It covers purpose, usage guidelines, parameter semantics, behavioral traits, error handling, and sibling tool relationships. The output schema existence means return values don't need explanation, and the description addresses all other aspects thoroughly.

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, the description fully compensates by providing detailed parameter explanations in the '参数说明' section. It clarifies required vs optional parameters, default values (limit=100, sort=desc), format requirements (millisecond timestamps), and practical usage guidance (call cls_convert_time for timestamps). This adds substantial value 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's purpose as '检索分析 CLS 日志' (search and analyze CLS logs) with specific mention of supporting both CQL retrieval and SQL pipeline analysis. It distinguishes itself from siblings like cls_describe_index and cls_describe_search_syntax by being the primary execution tool for log queries rather than metadata or syntax reference 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 explicit guidance on when to use this tool versus alternatives, including calling cls_convert_time for timestamp conversion, cls_describe_index for field verification before SQL analysis, and cls_describe_search_syntax for syntax reference when errors occur. It also distinguishes from siblings like cls_get_log_count and cls_get_log_histogram by being the comprehensive query tool.

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