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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool creates an OSS bucket but doesn't mention critical behavioral traits: whether this is a mutating operation (implied by 'create'), what permissions are required, potential costs, rate limits, or what happens on success/failure. For a creation tool with zero annotation coverage, this is a significant gap in 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 brief and front-loaded with the main purpose, but the structure is minimal. It uses a simple 'Args:' section for parameters, which is clear but lacks elaboration. While concise, it could be more informative without becoming verbose, especially given the lack of annotations and low schema coverage.

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 (creation operation), no annotations, 0% schema description coverage, but with an output schema (which handles return values), the description is partially complete. It covers the basic purpose and parameters but misses behavioral context, usage guidelines, and detailed parameter semantics. The output schema reduces the need to describe returns, but other gaps remain significant.

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 lists both parameters ('bucket_name' and 'region') with brief Chinese explanations, adding basic meaning beyond the schema's titles. However, it doesn't provide format constraints (e.g., bucket naming rules), region options beyond the default, or validation details. The description adds some value but doesn't fully compensate for the schema's lack of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as '创建OSS存储桶' (Create OSS bucket), which is a specific verb+resource combination. It distinguishes itself from sibling tools like 'list_oss_buckets' and 'delete_oss_bucket' by focusing on creation rather than listing or deletion. However, it doesn't explicitly differentiate from other creation tools in the sibling list, which mostly describe or manage resources rather than create them.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., permissions, account setup), when not to use it (e.g., if a bucket already exists), or refer to sibling tools like 'list_oss_buckets' for checking existing buckets. The absence of usage context leaves the agent to infer appropriate scenarios.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. While '删除' clearly indicates a destructive operation, it doesn't mention critical behavioral aspects like whether deletion is permanent, requires specific permissions, has rate limits, or what happens to contained objects. The description lacks essential context for a destructive operation.

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 brief but not optimally structured. The main purpose is stated in one line, followed by parameter translations. While concise, it could be more front-loaded with critical behavioral information for a destructive operation. The parameter section adds some value but could be integrated more efficiently.

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 destructive tool with 2 parameters, 0% schema coverage, no annotations, but with an output schema, the description is inadequate. It doesn't address the destructive nature sufficiently, provides minimal parameter guidance, and fails to give context about when this operation is appropriate versus dangerous. The output schema existence reduces but doesn't eliminate the need for more complete description.

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 Chinese translations of parameter names ('存储桶名称' for bucket_name, '区域ID' for region) but adds minimal semantic context beyond what's obvious from the parameter names. The description doesn't explain format requirements, constraints, or the significance of the default region 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 action ('删除' meaning delete) and resource ('OSS存储桶' meaning OSS bucket), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'list_oss_buckets' or 'create_oss_bucket' beyond the obvious action difference.

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. There's no mention of prerequisites (e.g., bucket must be empty), consequences, or when to choose other tools like 'list_oss_buckets' for verification first.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states it queries information without mentioning authentication requirements, rate limits, error conditions, pagination behavior, or what specific information is returned. For a query tool with zero annotation coverage, this 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 brief with two sentences, but the structure is basic. The first sentence states the purpose, the second documents the parameter. While efficient, it could be more front-loaded with key information and lacks formatting that would enhance readability for an AI agent.

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) and only one parameter, the description covers the basic purpose and parameter meaning. However, for a query tool with no annotations, it should ideally mention authentication needs, rate limits, or what kind of instance information is returned. The presence of an output schema elevates the score from what would otherwise be lower.

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 the only documentation for the single parameter 'region', explaining it's a region ID with an example 'cn-beijing'. Since schema description coverage is 0% and there's only one parameter, the description fully compensates by providing clear semantic meaning and an example, though it doesn't explain regional constraints or valid values.

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 '查询ECS实例信息' (Query ECS instance information), which provides a clear verb ('查询'/query) and resource ('ECS实例'/ECS instances). However, it doesn't differentiate from siblings like 'describe_ecs_regions' or 'describe_ecs_zones' - all describe ECS-related entities. The purpose is clear but lacks sibling distinction.

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

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

No guidance is provided about when to use this tool versus alternatives. There's no mention of when this tool is appropriate versus other ECS tools like 'reboot_ecs_instances', 'start_ecs_instances', or 'stop_ecs_instances', nor does it explain its relationship to 'describe_ecs_regions' or 'describe_ecs_zones'. The description only states what it does, not when to use it.

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 it's a query/list operation, implying read-only and non-destructive behavior, but doesn't disclose any behavioral traits like authentication needs, rate limits, pagination, or response format. For a tool with no annotations, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence in Chinese ('查询ECS可用区域列表'), directly stating the purpose without any fluff. It's appropriately sized and front-loaded, with every word earning its place.

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

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

Given the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description is minimally adequate. However, it lacks details on behavioral aspects (e.g., read-only nature, potential errors) that would be helpful since no annotations are provided. It's complete enough for a simple query tool but could be more informative.

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, and schema description coverage is 100% (empty schema). The description doesn't need to add parameter semantics beyond what's already clear—no inputs required. Baseline for 0 parameters is 4, as there's nothing to compensate for.

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 '查询ECS可用区域列表' clearly states the action (query/list) and resource (ECS regions/availability zones). It distinguishes from siblings like describe_ecs_instances (instances) and describe_ecs_zones (zones vs regions). However, it doesn't specify if this lists all regions or filtered ones, keeping it from a perfect score.

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 versus alternatives. Siblings include describe_ecs_zones (which might be more granular) and describe_ecs_instances (for specific instances), but the description doesn't mention these or provide context for selection. Usage is implied by the name but not articulated.

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 for behavioral disclosure. It only states it's a query operation ('查询'), implying read-only behavior, but doesn't mention authentication requirements, rate limits, pagination, error conditions, or what the output contains. For a tool with no annotation coverage, this is insufficient 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 concise with two sentences: one stating the purpose, one explaining the parameter. Both sentences earn their place, and the structure is clear with purpose first followed by parameter details. Minor deduction for not being perfectly front-loaded with all essential 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 has an output schema (which handles return values), 1 parameter, and no annotations, the description is minimally complete but has gaps. It covers the basic purpose and parameter, but lacks usage guidance and behavioral context that would be helpful for an AI agent. For a simple query tool with output schema, it's adequate but not 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?

With only 1 parameter and 0% schema description coverage, the description compensates well by providing the parameter name 'region' with a clear example ('如cn-beijing'). This adds meaningful semantic context beyond what the bare schema provides, though it doesn't explain format constraints or valid values beyond the example.

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ECS可用区列表' (Query ECS availability zone list), which is a specific verb+resource combination. It distinguishes from siblings like describe_ecs_instances or describe_ecs_regions by focusing specifically on zones. However, it doesn't explicitly differentiate from all siblings in the description text itself.

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. There are multiple describe_* siblings (describe_ecs_instances, describe_ecs_regions, describe_rds_instances, etc.) but no indication of when this specific zone-listing tool is appropriate versus other describe operations.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states it's a query operation, implying read-only behavior, but doesn't specify if it requires authentication, has rate limits, returns paginated results, or details the output format. The description adds minimal behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences: one stating the purpose and another explaining the parameter. It's front-loaded with the main action, and there's no redundant information. However, the use of Chinese might reduce clarity for some agents, and the structure could be slightly improved with clearer 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 1 parameter, no annotations, and an output schema exists, the description is minimally complete. It covers the basic purpose and parameter, but lacks details on behavioral traits, usage context, and output expectations, making it adequate but with clear gaps for effective tool 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 description includes an 'Args' section that explains the 'region' parameter with an example ('cn-beijing'), adding meaning beyond the input schema, which has 0% description coverage and only provides a default value. However, with only 1 parameter and partial documentation in the description, it meets the baseline for adequate but not comprehensive coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool's purpose as '查询RDS实例列表' (query RDS instance list), which clearly indicates it retrieves a list of RDS instances. However, it doesn't differentiate from sibling tools like 'describe_ecs_instances' beyond the resource type (RDS vs ECS), and the title is null, leaving some ambiguity about the exact scope.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or comparisons to sibling tools like 'describe_ecs_instances' or other describe_* tools, leaving the agent to infer usage based on the resource 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 carries the full burden. It states it queries a list, implying a read-only operation, but doesn't disclose behavioral traits such as whether it requires authentication, has rate limits, returns paginated results, or what the output format is. The description is minimal and lacks critical 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 brief and front-loaded with the main purpose, followed by parameter details in a structured 'Args:' section. It avoids unnecessary words, but the lack of broader context or guidelines means it might be too terse for optimal agent understanding.

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), 1 parameter with low schema coverage, and no annotations, the description is minimally adequate. It covers the purpose and parameter example but misses usage guidelines and behavioral transparency, leaving gaps for a read operation in a cloud management 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 description adds meaningful context for the single parameter 'region' by providing an example value ('cn-beijing'), which clarifies the expected format beyond the schema's generic 'string' type. With 0% schema description coverage and only 1 parameter, this compensates well, though it could specify if other regions are valid or if it's optional.

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 '查询VPC列表' which translates to 'Query VPC list', providing a clear verb ('query') and resource ('VPC list'). However, it doesn't distinguish this tool from sibling tools like 'describe_ecs_instances' or 'describe_rds_instances' beyond the resource type, making it somewhat generic within the context of this server.

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 doesn't mention prerequisites, context (e.g., for cloud infrastructure management), or compare it to related tools like 'describe_vswitches' (which might list subnets within VPCs). Usage is implied by the action but not explicitly stated.

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 only states it's a query operation, but doesn't disclose behavioral traits like authentication requirements, rate limits, pagination behavior, error conditions, or what happens when vpc_id is omitted. For a tool with no annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and well-structured: a single sentence stating the purpose followed by a clear parameter explanation section. Every sentence earns its place with no wasted words, and the information is front-loaded appropriately.

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 0% schema coverage, and no annotations, the description provides adequate basic purpose and parameter semantics. However, it lacks behavioral context needed for a query tool with no annotations, making it minimally complete but with clear gaps.

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

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

The description provides clear semantic meaning for both parameters: 'region' as region ID with an example (cn-beijing) and 'vpc_id' as VPC ID with indication it's optional. With 0% schema description coverage, this compensates well by explaining what each parameter represents, though it doesn't specify format constraints beyond the example.

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 '查询交换机列表' (query switch list), which clearly indicates the tool's purpose as retrieving a list of vSwitches. It specifies the resource (vSwitches) and action (query/list), but doesn't differentiate from siblings like describe_vpcs or describe_ecs_instances 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?

No guidance is provided about when to use this tool versus alternatives. The description doesn't mention sibling tools like describe_vpcs or describe_ecs_instances, nor does it specify any prerequisites, constraints, or appropriate contexts for using this tool.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves CPU usage data, implying a read-only operation, but doesn't clarify aspects like whether it requires specific permissions, rate limits, data freshness, error handling, or output format. For a monitoring tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded: the first line states the purpose clearly, followed by a brief parameter explanation. There's no wasted text, and the structure is logical. However, it could be slightly more concise by integrating the parameter details more seamlessly, but it's still efficient.

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

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

Given the tool's complexity (simple monitoring with 2 parameters), no annotations, and the presence of an output schema (which handles return values), the description is minimally adequate. It covers the purpose and parameters but lacks behavioral details like error cases or usage context. With the output schema reducing the need to explain returns, it meets a basic threshold but has clear gaps in guidance and transparency.

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

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

The description adds meaningful context beyond the input schema. The schema has 0% description coverage (titles only: 'Region' and 'Instance Ids'), but the description provides examples: '区域ID，如cn-beijing' (region ID, e.g., cn-beijing) and 'ECS实例ID列表' (ECS instance ID list). This clarifies the expected format and purpose of the parameters, compensating well for the low schema coverage. Since there are only 2 parameters, this is sufficient for a high 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ECS实例CPU使用率数据' (Get ECS instance CPU usage data). It specifies the verb (获取/get) and resource (ECS实例CPU使用率数据/ECS instance CPU usage data), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like get_disk_usage_data or get_memory_usage_data beyond the resource name, which is why it's 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 provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like describe_ecs_instances (which might list instances) or other monitoring tools, nor does it specify prerequisites or contexts for usage. The only implied usage is from the purpose, but no explicit when/when-not instructions are 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 carries the full burden of behavioral disclosure. It states the tool retrieves data ('获取'), implying a read-only operation, but doesn't clarify aspects like whether it requires specific permissions, rate limits, data freshness, or error conditions. For a data-fetching tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded: the first sentence states the purpose clearly, followed by a brief 'Args' section listing parameters. There's no unnecessary information, and each sentence serves a purpose. It could be slightly more structured with bullet points or clearer separation, but overall 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 tool has an output schema (which handles return values), the description covers the basic purpose and parameters. However, with no annotations and low schema coverage, it lacks context on behavioral traits like permissions or rate limits. For a simple data retrieval tool, this is minimally adequate but leaves room for improvement in guiding usage and transparency.

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

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

The description adds basic semantics for both parameters: 'region' is described as '区域ID，如cn-beijing' (region ID, e.g., cn-beijing), and 'instance_ids' as 'ECS实例ID列表' (ECS instance ID list). With schema description coverage at 0%, this compensates somewhat by explaining what the parameters represent. However, it doesn't provide details like format constraints, example values beyond one region, or how multiple instance IDs are handled, keeping it at a baseline level.

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ECS实例磁盘使用率数据' (Get ECS instance disk usage data). It specifies the verb '获取' (get) and resource 'ECS实例磁盘使用率数据' (ECS instance disk usage data), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'get_cpu_usage_data' or 'get_memory_usage_data' beyond the resource type, which prevents a perfect score.

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 doesn't mention sibling tools like 'get_cpu_usage_data' or 'get_memory_usage_data' for different metrics, or 'describe_ecs_instances' for general instance info. There's no context on prerequisites, such as needing instance IDs from another tool, or exclusions like unsupported instance types.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it indicates this is a data retrieval operation ('获取'), it doesn't describe important behavioral aspects like whether this requires specific permissions, whether it's a real-time or historical query, rate limits, error conditions, or what the output format looks like. For a data retrieval tool with zero annotation coverage, this is insufficient.

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 concise with a clear purpose statement followed by parameter documentation. The two-sentence structure is efficient, though the parameter documentation could be slightly more detailed given the lack of schema descriptions.

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 means the description doesn't need to explain return values), the description is minimally adequate for a data retrieval tool. However, with no annotations and incomplete parameter documentation (0% schema coverage), the description should provide more context about behavioral aspects and usage scenarios to be truly complete.

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 parameter documentation in the Args section, explaining that 'region' is a region ID like cn-beijing and 'instance_ids' is a list of ECS instance IDs. However, with 0% schema description coverage, the description compensates somewhat but doesn't provide complete parameter semantics - it doesn't explain format requirements, constraints, or provide examples beyond a single region example.

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ECS实例内存使用率数据' (Get ECS instance memory usage data). This specifies both the verb (get) and resource (ECS instance memory usage data). However, it doesn't differentiate from sibling tools like 'get_cpu_usage_data' or 'get_disk_usage_data' beyond mentioning memory specifically.

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 doesn't mention sibling tools like 'get_cpu_usage_data' or 'describe_ecs_instances', nor does it provide context about prerequisites, timing considerations, or appropriate use cases for memory usage data versus other metrics.

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 states the tool lists OSS buckets but doesn't disclose behavioral traits like whether it requires authentication, returns all buckets or paginated results, error conditions, or rate limits. This is a significant gap for a tool with no annotation coverage.

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 brief but lacks front-loading of critical information. It starts with the purpose, then lists parameters in a separate section, which is structured but could be more efficient. The two-sentence format is concise but under-specified, not earning full marks for conciseness.

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

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

Given one parameter with 0% schema coverage and an output schema exists, the description is minimally complete. It covers the purpose and parameter basics but lacks behavioral details and usage guidelines. The output schema reduces the need to explain return values, but overall completeness is adequate with clear gaps.

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

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

Schema description coverage is 0%, so the description must compensate. It adds the parameter 'region' with a brief explanation ('区域ID' meaning 'region ID'), which provides basic semantics beyond the schema's title 'Region'. However, it doesn't explain format, constraints, or default values, leaving gaps in parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('列出' meaning 'list') and resource ('OSS存储桶' meaning 'OSS buckets'). It distinguishes itself from siblings like create_oss_bucket and delete_oss_bucket by focusing on listing rather than creating or deleting. However, it doesn't specify scope (e.g., all buckets vs. filtered) which prevents a perfect score.

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 doesn't mention prerequisites, context for listing buckets, or differentiate from other listing tools (though none exist among siblings). Usage is implied by the name but not explicitly stated.

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 states the tool analyzes queries and converts them to expert recommendations, which implies it's a read-only analysis tool. However, it doesn't disclose behavioral details like response format, error conditions, or processing limitations. The description adds basic context about its analytical purpose but lacks depth about how it behaves.

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 perfectly concise with two clear components: the tool's purpose (understanding and converting queries) and explicit usage guidance (always use first). Every word serves a purpose, and the most important information (that this is the first tool to use) is front-loaded in the instruction.

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 no parameters, has an output schema (which handles return values), and performs a specific analytical function, the description provides adequate context. It clearly explains when and why to use this tool versus the operational sibling tools. The main gap is lack of detail about what kind of analysis or recommendations it produces, but the output schema should cover this.

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

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

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the parameter situation. The description appropriately doesn't discuss parameters since none exist. It focuses on the tool's purpose and usage context, which is the right approach for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '阿里云专家提示词理解' (Alibaba Cloud expert prompt understanding) with the specific action '理解针对阿里云的用户查询并转换为阿里云专家建议' (understand user queries about Alibaba Cloud and convert them into expert recommendations). It explicitly distinguishes itself from all sibling tools by being the first tool to use for query analysis rather than direct resource operations.

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

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

The description provides explicit usage guidance: '总是首先使用此工具' (always use this tool first) for understanding Alibaba Cloud user queries. This creates a clear workflow hierarchy where this tool precedes all other sibling tools that perform specific operations like creating/deleting resources or describing instances.

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 for behavioral disclosure. It states the action (restart) but doesn't describe critical behaviors: whether this requires specific permissions, if it's destructive (e.g., data loss risk), expected downtime, rate limits, or what happens if instances are already stopped. For a mutation tool with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded with the purpose in the first line, followed by parameter explanations. It avoids unnecessary details, though the structure could be slightly improved by separating purpose from args more clearly. Every sentence serves a 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 the tool's complexity (mutation with 2 parameters), no annotations, and an output schema (which reduces need to describe returns), the description is minimally adequate. It covers the action and parameters but lacks behavioral context, usage guidelines, and deeper parameter semantics. It's incomplete for safe and 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 compensate. It adds basic semantics: 'region' as region ID with an example (cn-beijing) and 'instance_ids' as a list of ECS instance IDs. However, it doesn't explain format constraints, validation rules, or optionality (both parameters have defaults but no required status). The description provides minimal value beyond the schema's structure.

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 '重启ECS实例' (Restart ECS instances), which clearly indicates the verb (restart) and resource (ECS instances). It distinguishes from siblings like start_ecs_instances and stop_ecs_instances by specifying the restart action, though it doesn't explicitly contrast them. The purpose is specific and unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives like start_ecs_instances or stop_ecs_instances. It lacks context about prerequisites (e.g., instance state), exclusions, or typical scenarios for restarting versus other operations. Usage is implied only by the action name.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool runs commands but doesn't describe critical behaviors: whether it requires specific permissions, if commands run as root or a user, timeout limits, output handling, or error conditions. For a command execution tool with zero annotation coverage, this leaves significant gaps in understanding its operational traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded: the first sentence states the purpose clearly, followed by a structured 'Args' section listing parameters with brief explanations. There's no wasted text, though it could be more polished (e.g., using bullet points instead of plain text). Every sentence adds value, making it 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 tool's complexity (command execution on cloud instances), no annotations, and an output schema exists (which covers return values), the description is minimally complete. It explains what the tool does and parameters but lacks behavioral context (e.g., security implications, execution environment). With the output schema handling returns, it's adequate but has clear gaps in safety and operational 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?

The description adds basic semantics for all 3 parameters (region, instance_ids, command) with examples like 'cn-beijing' for region and '要执行的命令' (command to execute). However, schema description coverage is 0%, so the schema provides no additional documentation. The description compensates somewhat but lacks details on parameter constraints (e.g., region format, instance ID validation, command length limits), keeping it at a baseline level.

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: '在ECS实例上运行命令' (run commands on ECS instances). It specifies the verb '运行' (run) and resource 'ECS实例' (ECS instances), making the action clear. However, it doesn't explicitly differentiate from sibling tools like 'reboot_ecs_instances' or 'start_ecs_instances', which are also ECS-related operations.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., instance must be running), exclusions (e.g., commands that require sudo), or compare it to sibling tools like 'describe_ecs_instances' for checking instance status before running commands. Usage is implied but not explicitly stated.

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 states the action ('启动') but lacks details on permissions required, rate limits, whether it's idempotent, what happens if instances are already running, or error conditions. For a mutation tool with zero annotation coverage, this is a significant gap in 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 appropriately sized and front-loaded, with the purpose stated first followed by parameter details. Every sentence adds value: the first defines the action, and the second explains parameters. However, the structure could be improved by separating purpose and parameters more clearly, and it's slightly verbose in the parameter explanations.

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 (mutation with 2 parameters), no annotations, and an output schema (which reduces need to describe returns), the description is minimally adequate. It covers the basic action and parameters but lacks behavioral context, usage guidelines, and detailed parameter semantics, making it incomplete for safe and effective use by an agent.

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

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

Schema description coverage is 0%, so the description must compensate. It adds basic semantics by explaining 'region' as a region ID with an example ('cn-beijing') and 'instance_ids' as a list of ECS instance IDs. However, it doesn't clarify format constraints (e.g., ID patterns), optionality, or interactions between parameters, leaving gaps despite the low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('启动' meaning 'start') and resource ('ECS实例' meaning 'ECS instances'), making the purpose immediately understandable. It distinguishes from siblings like 'stop_ecs_instances' and 'reboot_ecs_instances' by specifying the start action. However, it doesn't explicitly mention what 'start' entails (e.g., powering on virtual machines), keeping it from a perfect score.

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

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

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., instances must be stopped), compare to siblings like 'reboot_ecs_instances' or 'describe_ecs_instances', or specify use cases (e.g., resuming workloads). The absence of such context leaves the agent without direction on appropriate usage scenarios.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It only states the action ('停止') without explaining what 'stop' entails (e.g., graceful shutdown vs. forced stop, state changes, billing implications, or permissions required). This is inadequate for a destructive operation with zero annotation coverage.

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 brief and structured with a title and parameter list, but it's under-specified for a destructive tool. The two sentences earn their place by stating purpose and parameters, but more context is needed for safe usage, making it feel incomplete rather than optimally concise.

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 this is a destructive tool with no annotations, 2 parameters, 0% schema coverage, and an output schema (which helps), the description is incomplete. It covers basic purpose and parameters but misses critical behavioral details like effects, permissions, or error handling, leaving gaps for safe agent 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 description provides meaningful parameter semantics: 'region' is explained as '区域ID，如cn-beijing' (region ID, e.g., cn-beijing), and 'instance_ids' as 'ECS实例ID列表' (ECS instance ID list). With 0% schema description coverage, this compensates well by clarifying what each parameter represents, though it lacks format details like ID patterns or list constraints.

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 action ('停止' meaning 'stop') and resource ('ECS实例' meaning 'ECS instances'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'reboot_ecs_instances' or 'start_ecs_instances' beyond the basic verb difference, missing explicit scope or behavioral distinctions.

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

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

No guidance is provided on when to use this tool versus alternatives like 'reboot_ecs_instances' or 'start_ecs_instances'. The description lacks context about prerequisites, consequences, or typical use cases, offering only basic parameter documentation without usage context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states what the tool does (test connection status) without explaining what 'connection status' entails (e.g., network connectivity, API availability, authentication validity), what the output might include, or any side effects (e.g., rate limits, logging). For a diagnostic tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence ('测试阿里云连接状态') that directly states the tool's purpose without any fluff or redundancy. It is appropriately sized and front-loaded, making it highly efficient for an agent to parse quickly.

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, no annotations, but with an output schema), the description is minimally complete. It states the basic purpose, but lacks details on behavior, output interpretation, or usage context. The presence of an output schema means the description doesn't need to explain return values, but it should still cover more operational aspects to be fully helpful.

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, and the input schema has 100% description coverage (though empty). The description doesn't need to add parameter semantics, so it meets the baseline expectation. A score of 4 reflects that the description is adequate for a parameterless tool, though it could theoretically mention why no parameters are needed (e.g., uses default configurations).

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 '测试阿里云连接状态' (test Alibaba Cloud connection status), which is a specific verb ('test') + resource ('Alibaba Cloud connection'). However, it doesn't distinguish this from potential sibling tools that might also test connections or verify cloud service availability, so it falls short of a perfect score.

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 doesn't mention prerequisites (e.g., authentication setup), scenarios where connection testing is needed, or how it differs from other diagnostic tools in the sibling list like those for monitoring CPU/disk usage. This leaves the agent with minimal context for tool selection.

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