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 the tool generates videos and is simple/convenient, but doesn't disclose behavioral traits such as required permissions, rate limits, processing time, error conditions, or what the output looks like (e.g., video format, size). 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 poorly structured and verbose, with redundant examples and thinking processes that don't add essential value. It includes markdown headers and detailed user scenarios that could be condensed. Sentences like '思考过程:' and repetitive example details waste space without improving clarity, making it inefficient and hard to parse.

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

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

Given the complexity of a video generation tool with 4 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral aspects (e.g., mutations, side effects), output format, error handling, and differentiation from siblings. The examples add some context but don't compensate for the missing structural information, leaving significant gaps for an AI 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 100%, so the schema already documents all four parameters (inputText, voiceId, videoUrl, title). The description adds some context through examples, mentioning parameters like templateVideoId, driveType, text, person, and inputAudioUrl, but these don't directly map to the schema parameters and may confuse rather than clarify. Baseline 3 is appropriate as the schema does the heavy lifting.

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 generates digital human videos using real-person recorded videos and selected voice tones, with no requirements for video resolution or portrait generation. It specifies the action (generate), resource (digital human video), and scope (simple/convenient). However, it doesn't explicitly differentiate from siblings like generateDhVideo or generateLite2dGeneralVideo.

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 through examples showing simple video synthesis needs with video files/URLs, voice IDs, and text content. It doesn't explicitly state when to use this tool versus alternatives like generateDhVideo or generateLite2dGeneralVideo, nor does it provide exclusions or prerequisites. The examples suggest context but lack explicit 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 for behavioral disclosure. It mentions the tool generates videos but doesn't describe what happens after generation (e.g., where the video is stored, if it's returned immediately, processing time, or error conditions). The example implies it's a creation/mutation tool, but there's no information about permissions, rate limits, or side effects. This is a significant gap for a complex tool with 13 parameters.

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 poorly structured and verbose. It includes a lengthy example with a '思考过程' (thought process) section that walks through parameter mapping, which is redundant given the comprehensive schema. The front-loaded tool purpose is clear, but the example occupies most of the description without adding proportional value. The content could be significantly condensed while maintaining utility.

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 (13 parameters, no annotations, no output schema), the description is incomplete. It focuses heavily on parameter mapping in an example but lacks critical context: what the tool returns (no output schema), behavioral traits like processing time or storage, and differentiation from sibling tools. For a video generation tool with many configuration options, this leaves significant gaps for an AI agent to understand proper usage.

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

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

Schema description coverage is 100%, so the schema already documents all 13 parameters thoroughly. The description adds minimal value beyond the schema: it mentions FigureId, driveType, text, person, inputAudioUrl, width, height, cameraID, enable, backgroundimageUrl, and autoAnimoji in the example, but these are already well-documented in the schema with descriptions and defaults. No additional semantic context is provided beyond what's in the structured 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: '根据所选数字人像ID及发音人ID，生成数字人视频' (generate digital human video based on selected figure ID and voice ID). It specifies the verb '生成' (generate) and resource '数字人视频' (digital human video), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like generateDh123Video or generateLite2dGeneralVideo, which appear to be similar video generation tools.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. While it mentions a '思考过程' (thought process) that suggests using this tool for complex video generation with specific parameters, it doesn't name alternative tools or specify exclusion criteria. The example shows usage but lacks comparative context with siblings like generateDh123Video or generateText2Audio.

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 mentions the tool is for '基础视频制作' (basic video production) and uses '通用口型驱动' (generic mouth shape driving), which adds some behavioral context. However, it lacks critical details: whether this is a read/write operation, permission requirements, rate limits, processing time, or what happens to the input video. For a tool that likely creates resources, 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 poorly structured: it starts with a header '#工具说明：' followed by an example that dominates the text. The example includes unnecessary '思考过程' (thinking process) that doesn't belong in a tool description. While the core purpose is stated, the formatting wastes space and reduces clarity, making it less front-loaded and 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 no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a video ID, status object), error conditions, or prerequisites (e.g., needing uploadFiles first). For a 5-parameter tool that likely creates digital avatars, more context on behavior and results is needed 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?

Schema description coverage is 100%, so the schema already documents all 5 parameters with descriptions. The description adds minimal value: it names parameters (name, gender, keepBackground, templateVideoId) in the example and implies templateVideoId comes from uploadFiles. However, it doesn't explain maskVideoId or provide deeper semantic context beyond what the schema offers, meeting the baseline for high 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 tool's purpose: '根据上传真人录制的视频生成数字人像' (generate a digital avatar from uploaded real-person video). It specifies the resource (digital avatar) and verb (generate), and distinguishes it from siblings like generateText2Audio or generateVoiceCloneLite. However, it doesn't explicitly differentiate from generateDh123Video or generateDhVideo, which might have similar purposes.

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

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

The description provides some usage context: '仅可用于基础视频制作，数字人使用通用口型驱动' (only for basic video production, digital avatar uses generic mouth shape driving). This implies when to use it (basic video needs) but doesn't explicitly state when not to use it or name alternatives among siblings. The example helps illustrate usage but doesn't provide comprehensive guidelines.

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 mentions that the tool generates audio without video, but doesn't cover critical aspects like whether this is a read-only or mutation operation, authentication requirements, rate limits, error handling, or what the output looks like (e.g., audio format, file location). For a tool with no annotations, 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 moderately concise but includes unnecessary elements. The first sentence states the purpose clearly, but the example and '思考过程' (thinking process) section add bulk without essential information, making it less front-loaded. It could be more streamlined by focusing on core usage rather than illustrative narratives.

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 (audio generation tool with no annotations and no output schema), the description is incomplete. It lacks details on output (e.g., what is returned, audio format), error cases, dependencies (e.g., voiceId from getVoices), and behavioral traits. For a tool that likely involves mutation and external resources, this leaves the agent with insufficient context to use it effectively.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (text and voiceId) with descriptions. The description adds minimal value: it mentions text and person (though the actual parameter is voiceId) in the example, but doesn't provide additional semantics like constraints, examples beyond the schema, or how voiceId relates to getVoices. Baseline 3 is appropriate when the schema does most of the work.

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: '根据提供的文本内容及选定音色，无需生成视频，生产对应的音频' (generate corresponding audio from provided text content and selected voice, without generating video). This specifies the verb (generate audio), resources (text and voice), and scope (no video). However, it doesn't explicitly distinguish this from sibling tools like generateVoiceCloneLite or getText2AudioStatus, which reduces 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?

The description provides minimal usage guidance. The example shows when to use this tool (when a user wants to generate audio from text with a specific voice), but it doesn't explain when NOT to use it or mention alternatives like generateVoiceCloneLite for voice cloning or getText2AudioStatus for checking status. No explicit context or prerequisites are stated beyond the example.

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 mentions the tool generates voice clones for synthesis/video, but doesn't cover critical behaviors: whether this creates a persistent resource, what permissions/authentication are needed, rate limits, or what happens on failure. The example shows parameter usage but lacks 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 front-loaded with the core purpose, but includes an extensive example that occupies most of the text. While the example is helpful, it could be more concise. The structure mixes tool explanation with instructional content, making it somewhat verbose for a tool description.

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

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

For a tool with 5 parameters, no annotations, and no output schema, the description is incomplete. It explains what the tool does and provides an example, but misses critical context: what the tool returns (no output schema), error conditions, prerequisites (e.g., needing uploaded audio first via 'uploadFiles'), and how the generated voice clone integrates with sibling tools.

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

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description's example illustrates parameter usage (e.g., 'name的值为zhangsan'), but doesn't add meaningful semantic context beyond what's in the schema descriptions. This meets the baseline for high 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 tool's purpose: '根据上传音频生成音色，可用于语音合成及视频制作' (generate voice clone from uploaded audio for speech synthesis and video production). This specifies the verb (generate), resource (voice clone), and application context. However, it doesn't explicitly differentiate from sibling tools like 'generateText2Audio' or 'getVoices', 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. While it includes an example showing how to use the tool, it doesn't mention when NOT to use it or what sibling tools might be better for different scenarios. The example is instructional but not comparative.

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 queries progress, implying it's a read-only operation, but doesn't disclose behavioral traits such as authentication requirements, rate limits, error handling, or what the response format looks like (e.g., progress percentage, status codes). The example adds minimal context but leaves key operational details 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 poorly structured and includes redundant elements. It starts with a tool explanation but devotes most space to a verbose example with unnecessary '思考过程' (thinking process) that doesn't add value for an AI agent. The core information is buried, and the example could be condensed or omitted to improve clarity and efficiency.

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 no annotations, no output schema, and a simple parameter, the description is incomplete. It lacks details on what the tool returns (e.g., status indicators, progress values), error conditions, or how it integrates with sibling tools like 'generateDh123Video'. For a query tool in a video synthesis context, more operational context is needed to guide 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?

The input schema has 100% description coverage, with the parameter 'taskId' documented as '视频任务ID' (video task ID). The description mentions '工具需要task ID这些参数' (the tool needs task ID parameters), adding no meaningful semantics beyond the schema. Since schema coverage is high, the baseline score of 3 is appropriate, as the description doesn't compensate with additional details like format examples or 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 tool's purpose: '查询123数字人视频合成进度' (query 123 digital human video synthesis progress). It specifies the verb '查询' (query) and resource '123数字人视频' (123 digital human video). However, it doesn't explicitly distinguish this tool from sibling tools like 'getDhVideoStatus' or 'getLite2dGeneralStatus', which likely serve similar purposes for different video types.

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 includes a usage example that implies when to use this tool: when a user wants to check if a video with a specific task ID is ready. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'getDhVideoStatus' or 'getLite2dGeneralStatus', nor does it mention any prerequisites or exclusions. The example helps but lacks comprehensive context.

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

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

No annotations are provided, so the description carries the full burden. It mentions the tool queries progress but doesn't disclose behavioral traits like what the response format includes (e.g., status codes, error handling), whether it's idempotent, or any rate limits. The example implies it returns results or requires fallback, but this is vague. More details on behavior would improve 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 poorly structured and verbose, including a markdown header, example, and step-by-step thinking process that doesn't belong in a tool description. It's front-loaded with unnecessary commentary rather than focusing on concise, actionable information. Sentences like '思考过程:' (thinking process) add clutter without earning their 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 no annotations and no output schema, the description is incomplete for a tool that queries status. It lacks details on return values (e.g., what progress indicators are provided), error conditions, or how to interpret results. The example hints at fallback behavior but doesn't fully explain it. For a status-checking tool, this leaves significant gaps in understanding its operation.

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

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

Schema description coverage is 100%, with the parameter 'taskId' clearly documented in the schema as '基础数字人视频任务ID' (basic digital human video task ID). The description adds minimal value beyond this, only noting in the example that '工具需要task ID这些参数' (the tool needs task ID parameters). It doesn't provide additional semantics like format constraints or usage tips, so the baseline score of 3 is appropriate.

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

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

The description states the tool '查询基础数字人视频合成进度' (query basic digital human video synthesis progress), which is a clear verb+resource combination. However, it doesn't explicitly distinguish this tool from its sibling 'getDh123VideoStatus', which appears to serve a similar purpose for a different type of digital human video. The description mentions both tools in the example but doesn't clarify their distinct scopes.

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: after calling 'generateDhVideo' to check progress. It explicitly mentions 'getDh123VideoStatus' as an alternative if no results are found, offering guidance on tool selection. However, it doesn't specify when NOT to use this tool or address other potential alternatives among 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 of behavioral disclosure. It only states the tool queries portrait IDs, without mentioning whether this is a read-only operation, if it requires authentication, what the return format looks like, or any rate limits. For a query tool with zero annotation coverage, this leaves critical behavioral traits undocumented.

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—just one phrase in Chinese. While this avoids waste, it's arguably under-specified rather than efficiently structured. It lacks front-loading of key details and doesn't provide a complete overview, making it feel sparse 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 the tool's complexity (a query operation with one parameter) and the absence of both annotations and an output schema, the description is incomplete. It doesn't explain what the tool returns, how results are formatted, or any behavioral nuances. For a tool with no structured output documentation, the description should provide more context 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 input schema has 100% description coverage, with the single parameter 'systemFigure' well-documented in the schema itself. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline of 3 where the schema does the heavy lifting. No compensation is needed given the high 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 '查询可用的人像ID' (query available portrait IDs), which provides a basic verb+resource combination. However, it's somewhat vague about what 'available portrait IDs' means in practice, and it doesn't differentiate this tool from sibling tools like 'getVoices' or other query tools. The description is functional but lacks specificity about scope or 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 no guidance on when to use this tool versus alternatives. There are multiple sibling query tools (e.g., getVoices, getDh123VideoStatus), but the description doesn't explain how this tool differs or when it's appropriate. No context, exclusions, or prerequisites are mentioned, leaving usage unclear.

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 it explains the dual-purpose nature and provides example parameter configurations, it doesn't describe important behavioral aspects: whether this is a read-only operation (implied but not stated), what the response format looks like, pagination behavior (mentioned in examples but not explained), error conditions, or rate limits. The examples help but don't constitute comprehensive behavioral 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 front-loaded with a clear purpose statement, but includes lengthy example sections with detailed '思考过程' (thought process) that could be more concise. While the examples are helpful, they contain redundant explanations and could be streamlined. The structure is logical (purpose → examples) but the examples themselves are verbose and could be condensed while preserving their instructional 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 dual-purpose nature (status queries AND listing available figures), 3 parameters, no annotations, and no output schema, the description is moderately complete. It covers the main use cases and parameter interactions well through examples, but lacks information about response format, error handling, and pagination details (though pagination parameters are mentioned in examples). For a tool with no output schema, more information about what to expect in return would be beneficial.

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

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

The input schema has 100% description coverage, providing good baseline documentation for all 3 parameters. The description adds significant value beyond the schema by explaining parameter semantics through practical examples: it shows how figureId should be set for status queries vs. listing queries, clarifies that systemFigure=false for custom figures, and demonstrates trainSuccess usage patterns. This contextual guidance helps users understand how parameters interact to achieve different outcomes.

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: '根据2D小样本数字人对应的人像ID，查询该任务目前的状态，也可以用于查询有哪些可用的2D人像' (Query the status of a 2D digital human generation task based on figure ID, or query available 2D figures). This specifies both primary and secondary uses with clear verbs ('查询' - query) and resources ('任务状态' - task status, '可用人像' - available figures). It doesn't explicitly differentiate from sibling tools like 'getFigures', but the dual-purpose nature is well-defined.

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 implied usage guidance through two examples: Example 1 shows when to use for checking task status (with figureId specified), and Example 2 shows when to use for listing available figures (with figureId empty and trainSuccess=true). However, it doesn't explicitly state when NOT to use this tool or mention alternatives like 'getFigures' for similar queries, leaving some ambiguity about tool selection.

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 mentions the tool queries progress but doesn't disclose behavioral traits like whether it's read-only, what the response format is (e.g., progress percentage, status codes), error handling, or rate limits. The example shows it requires a task ID, but this is already in the schema. It adds minimal context beyond basic 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 poorly structured, mixing tool explanation with an example and 'thinking process' in Chinese. It includes redundant elements like '#工具说明：' and step-by-step reasoning that don't add value for an AI agent. Sentences like '思考过程:' and numbered steps are wasteful, making it longer than necessary without improving clarity.

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

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

Given no annotations and no output schema, the description is incomplete for a status-checking tool. It doesn't explain what the tool returns (e.g., status values like 'processing', 'completed', or error details), how to interpret results, or prerequisites (e.g., task ID must be valid). The example helps but doesn't cover behavioral context needed 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 100%, with the single parameter 'taskId' documented as '语音合成任务ID' (audio synthesis task ID). The description adds no additional meaning beyond the schema—it reiterates that the tool needs 'task ID这些参数' (task ID parameters) in the example, but this doesn't enhance semantics. With high schema coverage, the baseline is 3, and the description doesn't compensate further.

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 '查询音频合成进度' (query audio synthesis progress), which is a specific verb+resource combination. It distinguishes from sibling tools like 'generateText2Audio' (which creates audio) and 'getVoices' (which lists voices). However, it doesn't explicitly differentiate from other status-checking siblings like 'getDh123VideoStatus' or 'getVoiceCloneStatus' beyond the audio focus.

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 an example scenario ('查一下taskid为xxx的语音合成好了没有') that implies usage when a user wants to check if a specific audio synthesis task is complete. It doesn't explicitly state when NOT to use this tool or name alternatives (e.g., using other status tools for video tasks). The example guides usage but lacks explicit exclusions or comparisons to 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 full burden. It describes a query operation ('查询' - query) which implies read-only behavior, but doesn't disclose any behavioral traits like authentication needs, rate limits, error conditions, or what the status response might contain. The example mentions parameters but doesn't explain tool behavior beyond the basic query intent. Significant gaps remain 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 poorly structured with a mix of tool explanation and example thinking process. The first sentence is useful, but the example section includes unnecessary implementation details ('思考过程' - thinking process) that don't belong in a tool description. This creates clutter and reduces clarity. The description is not appropriately front-loaded with 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 no annotations, no output schema, and 1 parameter with good schema coverage, the description is incomplete. It explains the basic purpose but lacks crucial context: what status values might be returned, error handling, authentication requirements, or typical use patterns. For a status-checking tool that likely returns important state information, this leaves too many unanswered questions for effective agent 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 100% with one parameter ('perId' described as '音色克隆任务的ID' - voice clone task ID). The description adds minimal value beyond the schema: it mentions 'perId' in the example but doesn't provide additional semantics like format requirements, valid ranges, or relationship to other parameters. Since schema coverage is high, baseline 3 is appropriate even with limited param info in description.

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 '查询该任务目前的状态' (queries the current status of the task), which is a clear verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'getDh123VideoStatus' or 'getText2AudioStatus', which likely serve similar status-checking purposes for different resource types. The purpose is understandable but lacks sibling differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It mentions a specific use case in the example ('查一下id为xxx的声音克隆好了没有' - check if voice clone with ID xxx is ready), but doesn't explain when this tool is appropriate compared to other status-checking tools or when not to use it. No explicit alternatives or context boundaries are provided.

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

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

No annotations are provided, so the description carries the full burden. It describes the tool's function and parameter usage through examples, but lacks critical behavioral details such as whether this is a read-only operation, potential rate limits, authentication requirements, or what the output format looks like. The examples add some context but don't fully compensate for the missing 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 overly verbose and poorly structured, consisting of lengthy example scenarios with thought processes rather than a clear, front-loaded explanation. It wastes space on hypothetical user interactions instead of concisely stating the tool's purpose and usage. Every sentence doesn't earn its place, as the examples could be condensed or replaced with direct guidelines.

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

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

Given no annotations and no output schema, the description is incomplete. It explains parameter usage through examples but fails to describe the tool's behavior, output format, or any constraints. For a tool with one parameter and no structured output documentation, the description should provide more comprehensive context about what the tool returns and how to interpret results.

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 100%, with the parameter 'isSys' well-documented in the schema. The description adds value through examples that illustrate how to interpret and use the parameter in different scenarios (e.g., setting to 'false' for cloned voices, omitting for all voices), but doesn't provide additional semantic information beyond what's in the schema. Baseline 3 is appropriate given the high 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 states the tool '查询可用的发音人ID' (queries available voice IDs), which is a clear purpose. However, it doesn't differentiate from siblings like 'getFigures' or 'getVoiceCloneStatus' that might also retrieve voice-related data. The description focuses on examples rather than a concise statement of what the tool does.

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

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

The description provides explicit usage guidance through two detailed examples, showing when to use the tool (to query voice IDs) and how to handle the parameter (isSystem). It implies usage for both cloned and system voices, but doesn't explicitly state when not to use it or compare to alternatives among 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions uploading files but doesn't describe what happens after upload (e.g., file processing, storage location, success/failure responses), authentication requirements, rate limits, file size restrictions, or error conditions. The example shows parameter mapping but lacks 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 poorly structured with mixed Chinese/English and markdown formatting that doesn't add value. It includes an overly detailed example that occupies most of the description rather than concise explanatory text. The content isn't front-loaded with clear purpose - it starts with a heading in Chinese followed by an example rather than a clear statement of what the tool does.

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 file upload tool with 3 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns, error conditions, file requirements, or how uploaded files integrate with sibling tools. The example provides some context but doesn't compensate for missing behavioral and operational information needed for proper 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?

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds minimal value by showing an example mapping in Chinese, but doesn't provide additional semantic context beyond what's in the schema (e.g., file format requirements, business type implications). Baseline 3 is appropriate when schema does the heavy lifting.

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 uploads files based on business type, which gives a general purpose. However, it doesn't specify what kind of files or what happens after upload, and doesn't clearly distinguish from sibling tools like generateVoiceCloneLite that might also involve file processing. The purpose is vague rather than 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 provides an example scenario but no explicit guidance on when to use this tool versus alternatives. It mentions 'business type' but doesn't explain when to choose OPEN_CUSTOMIZATION_2D_GENERAL vs OPEN_TTS_CLONE_LITE, or when to use uploadFiles versus other tools like generateVoiceCloneLite. There's no when-not-to-use guidance or prerequisites mentioned.

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