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. The statement 'Ark-only 模式下不支持该工具' suggests the tool may be unavailable or non-functional in certain contexts, but provides no information about what the tool actually does, its effects, limitations, or operational behavior when it IS supported.

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?

While technically concise (one sentence), the description is under-specified rather than appropriately concise. It fails to provide any functional information about the tool, making it ineffective despite its brevity. The single sentence doesn't earn its place as it doesn't describe the tool's purpose or usage.

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

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

The description is completely inadequate for a 3-parameter tool with no annotations and no output schema. It provides no functional information about what the tool does, when to use it, or what results to expect. Given the complexity suggested by the name 'action-imitation' and three required parameters, this description fails to provide any meaningful 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 schema description coverage is 100%, with all three parameters (referenceAction, targetCharacter, style) having clear descriptions in the input schema. The tool description adds no additional parameter information beyond what's already documented in the schema, 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 'Ark-only 模式下不支持该工具' (This tool is not supported in Ark-only mode) provides no information about what the tool actually does. It's a restriction statement rather than a functional description, making it completely misleading about the tool's purpose. The name 'action-imitation' suggests some form of action replication, but the description contradicts this by stating it's unsupported.

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. It only states that it's not supported in a specific mode, but gives no information about when it IS supported or appropriate to use. There's no comparison to sibling tools or indication of the tool's intended use case.

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. However, the description only mentions a mode restriction and does not disclose any behavioral traits such as what the tool does, its effects (e.g., creation, modification), authentication needs, rate limits, or output behavior. This leaves the agent with no understanding of the tool's 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 a single, concise sentence that is front-loaded with its only piece of information. There is no wasted text or unnecessary elaboration, making it efficient in structure, though it lacks substantive content.

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

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

Given the tool's complexity (4 required parameters, no annotations, no output schema), the description is highly incomplete. It fails to explain what the tool does, its purpose, or how to use it effectively. The lack of annotations and output schema means the description should provide more context, but it does not, leaving critical gaps in understanding.

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 clear descriptions for all four parameters (e.g., '数字人行为描述' for prompt). The description adds no additional meaning beyond the schema, as it does not mention parameters at all. According to the rules, with high schema coverage (>80%), the baseline score is 3, even without param info in the 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 'Ark-only 模式下不支持该工具' (Ark-only mode does not support this tool) does not state what the tool does. It only provides a restriction about when it cannot be used, offering no information about its actual purpose or function. This is a tautology that restates nothing about the tool's name or title, making it completely unhelpful for understanding the tool's intent.

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 a partial usage guideline by stating the tool is not supported in 'Ark-only mode,' but it does not explain when to use this tool versus alternatives, what contexts it is intended for, or any prerequisites. It lacks explicit guidance on when/when-not to use it, making it insufficient for effective 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?

With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. It mentions the model ('火山方舟 Seedream') and platform restriction ('Ark-only'), but doesn't describe rate limits, authentication needs, cost implications, output format, or whether it's a read/write operation. For a complex image generation tool with 7 parameters, this leaves significant gaps in understanding how the tool 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 extremely concise - just one sentence in Chinese. It's front-loaded with the core functionality and includes a platform restriction note. While efficient, it might be too brief for such a complex tool with many parameters and sibling alternatives, potentially sacrificing clarity for brevity.

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 complex image generation/editing tool with 7 parameters, no annotations, no output schema, and multiple similar siblings, the description is inadequate. It doesn't explain what '编辑图片' (edit images) means operationally, how generation differs from editing, what the output looks like, or how this tool relates to its siblings. The minimal description leaves too many contextual questions unanswered.

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 adds no parameter-specific information beyond what's in the schema. It mentions the model name which aligns with the 'model' parameter enum, but provides no additional context about parameter interactions or usage patterns. 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 clearly states the tool's purpose: '使用火山方舟 Seedream 模型生成/编辑图片' (generate/edit images using Volcano Ark Seedream model). It specifies the model and action (generate/edit), but doesn't distinguish from sibling tools like 'generate-img-seedream4', 'text-to-image', or 'image-to-image' that likely have overlapping functionality. The '(Ark-only)' qualifier adds specificity but not 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. With multiple image generation siblings (generate-img-seedream4, text-to-image, image-to-image, image-dressing), there's no indication of which scenarios favor this tool. The '(Ark-only)' note suggests platform restriction but doesn't help choose between similar tools.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. The description only states what the tool does at a high level ('直接调用...生成图片') without any information about rate limits, authentication requirements, error conditions, response format, or performance characteristics. For an image generation API with no annotation coverage, this is completely inadequate.

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 (one sentence) and front-loaded with the core functionality. Every word serves a purpose, though it could benefit from slightly more detail given the lack of annotations. The structure is clear but minimal.

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 an image generation API, no annotations, and no output schema, the description is severely incomplete. It doesn't explain what the tool returns, error conditions, authentication needs, rate limits, or any behavioral characteristics. The 100% schema coverage helps with parameters, but overall context is missing for proper tool understanding.

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 4 parameters thoroughly. The description adds no parameter information beyond what's in the schema - it doesn't explain parameter relationships, provide examples, or add context about how parameters interact. This meets the baseline expectation when schema coverage is high.

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 ('直接调用' - directly call) and target resource ('火山方舟 Seedream API 生成图片' - Volcanic Ark Seedream API to generate images), which is specific. It distinguishes from siblings by specifying 'Ark-only' (though this is more of a platform restriction than functional differentiation). However, it doesn't explicitly differentiate from similar tools like 'generate-image' or 'text-to-image' in the sibling list.

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. With siblings like 'generate-image', 'text-to-image', and 'image-to-image' available, there's no indication of what makes this tool different or when it should be preferred. The 'Ark-only' note suggests platform restriction but doesn't help with tool selection decisions.

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 mentions the asynchronous nature, it doesn't describe what 'asynchronous task' entails operationally - no information about task queuing, expected completion times, error handling, or how results are delivered. For a complex 12-parameter tool with no annotations, 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 a single, efficient Chinese sentence that conveys the core functionality. It's appropriately concise and front-loaded with the main purpose. However, given the tool's complexity, more context would be beneficial, so it's not a perfect 5.

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 complex video generation tool with 12 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns (task ID? status? video URL?), how to handle the asynchronous result, or any operational constraints. The description should provide more context about the asynchronous workflow and expected outputs.

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 adds no additional parameter semantics beyond what's in the schema. It doesn't explain relationships between parameters (like how imageUrl enables image-to-video) or provide usage examples. Baseline 3 is appropriate when schema does all the parameter documentation.

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 ('generate video') and specifies the model ('Seedance model') and execution mode ('asynchronous task'). It distinguishes from sibling tools like generate-image and text-to-image by focusing on video generation. However, it doesn't explicitly differentiate from generate-digital-human, which might also produce video content.

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 when to choose video generation over image generation tools, nor does it specify prerequisites or constraints for using this asynchronous video generation service.

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. However, the description does not disclose any behavioral traits—it doesn't explain what the tool does, its effects, permissions required, rate limits, or output format. It only mentions a mode restriction, which is insufficient for understanding the tool's behavior.

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

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

The description is concise but under-specified—it's a single sentence that fails to convey the tool's purpose or usage. While it's brief, it doesn't earn its place by providing necessary information. Conciseness should not come at the cost of clarity, making this inefficient rather than appropriately sized.

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 implied by the tool name and sibling tools (e.g., image processing), the description is incomplete. With no annotations, no output schema, and a description that only states a restriction, it fails to provide enough context for an agent to understand or use the tool effectively. The description does not compensate for the lack of structured data.

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

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

The input schema has 100% description coverage, with clear parameter descriptions in Chinese ('模特图片URL' for modelImageUrl and '服装图片URL' for garmentImageUrl). The description adds no additional meaning beyond the schema, but since schema coverage is high (>80%), the baseline score is 3. The description does not compensate or detract from the schema's parameter documentation.

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 'Ark-only 模式下不支持该工具' (This tool is not supported in Ark-only mode) does not state what the tool does. It's a restriction notice rather than a functional description. The name 'image-dressing' suggests dressing an image, but the description provides no clarification about the tool's actual purpose or how it differs from siblings like 'image-to-image' or 'generate-image'.

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 only states that the tool is not supported in Ark-only mode, with no guidance on when to use it versus alternatives. It does not provide any context on appropriate scenarios, prerequisites, or comparisons to sibling tools such as 'image-to-image' or 'generate-image'. This leaves the agent with no actionable usage information.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool performs image-to-image generation using a specific model, implying a generative/mutation operation, but doesn't disclose critical traits like whether it's read-only or destructive, authentication requirements, rate limits, output format, or error handling. For a tool with 5 parameters and no annotation coverage, this is a significant gap in 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 a single, efficient sentence in Chinese that directly states the tool's core function and model constraint. It's appropriately sized and front-loaded with the essential information, with no wasted words. However, it could be slightly more structured by explicitly separating purpose from constraints for better readability.

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

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

Given the tool's complexity (5 parameters, nested objects, no output schema, and no annotations), the description is incomplete. It lacks information about the output (e.g., image format, URL structure), error conditions, usage limits, and how it differs from sibling tools. For a generative tool with multiple parameters and platform-specific constraints, more context is needed to help the agent 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?

The description adds no parameter-specific information beyond what's already in the input schema, which has 100% schema description coverage. The schema thoroughly documents all 5 parameters (prompt, imageUrl, ratio, localPath, model) with descriptions, constraints, and enums. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't compensate with additional semantic context.

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 '使用火山方舟 Seedream 模型进行图生图（Ark-only）', which translates to 'Use Volcano Ark Seedream model for image-to-image (Ark-only)'. This specifies the verb ('进行图生图' - perform image-to-image), resource ('火山方舟 Seedream 模型' - Volcano Ark Seedream model), and platform constraint ('Ark-only'). It distinguishes from siblings like 'text-to-image' by focusing on image-to-image transformation rather than text-based generation. However, it doesn't explicitly differentiate from 'generate-img-seedream4' which might be similar.

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 'Ark-only', which might imply a platform restriction, but doesn't explain when to choose this over other image generation tools like 'generate-image', 'generate-img-seedream4', or 'text-to-image'. There's no mention of prerequisites, use cases, or exclusions, leaving 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.

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the model provider and exclusivity ('Ark-only'), it doesn't describe important behavioral aspects such as rate limits, authentication requirements, response format, error conditions, or whether the operation is idempotent. For a generative AI tool with no annotation coverage, this represents 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 extremely concise - a single Chinese sentence that efficiently communicates the core functionality and platform specificity. There's no wasted language or redundancy. The structure is front-loaded with the essential information: tool purpose and model provider.

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 complex image generation tool with 7 parameters, no annotations, and no output schema, the description is insufficiently complete. While concise, it doesn't address critical contextual information such as output format (image URL? binary data?), error handling, rate limits, or how it differs from similar sibling tools. The absence of annotations and output schema means the description should provide more comprehensive 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 provides no parameter-specific information beyond what's already documented in the input schema, which has 100% coverage. All 7 parameters (prompt, ratio, style, model, model_version, image_urls, add_watermark) are well-described in the schema with clear descriptions and enums where applicable. The description adds no additional context about parameter usage, constraints, or interactions.

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: '生成图片' (generate images) using the '火山方舟 Seedream 模型' (Volcano Ark Seedream model). It specifies the model provider and includes '(Ark-only)' to indicate exclusivity. However, it doesn't explicitly differentiate from sibling tools like 'generate-image' or 'generate-img-seedream4', which appear to offer similar functionality.

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. It mentions '(Ark-only)' which suggests this tool is specific to the Volcano Ark platform, but offers no explicit guidance on when to use this tool versus the sibling tools like 'generate-image' or 'generate-img-seedream4'. There's no mention of prerequisites, alternatives, or specific scenarios where this tool is preferred.

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