Server Quality Checklist

Tool Scores

• generate_videoA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns a task ID requiring follow-up with query_video_task, which is useful behavioral context. However, it lacks details on permissions, rate limits, costs, or error handling, which are important for a video generation tool.

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

  Conciseness4/5

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

  The description is well-structured with clear sections (overview, supported features, parameter explanations, return info). It is appropriately sized for an 8-parameter tool, though some details like model descriptions could be slightly more concise. Every sentence adds value.

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

  Completeness4/5

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

  Given the complexity of an 8-parameter video generation tool with no annotations and no output schema, the description does a good job explaining functionality, parameters, and the asynchronous result-checking process. It could improve by adding more behavioral context (e.g., execution time, limitations), but it covers the essentials adequately.

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

  Parameters4/5

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

  Schema description coverage is 100%, so the baseline is 3. The description adds value by grouping parameters into functional contexts (e.g., model choices explained with quality/speed trade-offs, supported durations/framerates/resolutions listed), which helps the agent understand parameter implications beyond the schema's technical specs.

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

  Purpose5/5

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

  The description clearly states the tool uses the Doubao Seedance model to generate video, with specific supported functionalities listed: text-to-video, image-to-video, and reference-image-to-video. It distinguishes from sibling tools by focusing on video generation (vs. generate_image for images and query_video_task for querying results).

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

  Usage Guidelines4/5

  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 by listing its three supported functionalities, but it does not explicitly state when to use it versus alternatives or any exclusions. It mentions the need to use query_video_task to check results, which is helpful guidance.

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

• generate_imageA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses important behavioral traits: the tool generates images using a specific AI model, supports multiple generation modes, has default values for optional parameters, requires specific permissions for direct model use, and includes error handling guidance for InvalidEndpointOrModel.NotFound. It doesn't mention rate limits, costs, or output format details.

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

  Conciseness5/5

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

  The description is well-structured with clear sections (功能, 参数说明, 重要提示), uses bullet points for readability, and every sentence adds value. It's appropriately sized for an 8-parameter tool with multiple functionalities and includes troubleshooting information without being verbose.

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

  Completeness4/5

  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 8 parameters, 100% schema coverage, and no output schema, the description is quite complete. It covers purpose, usage modes, parameter semantics, and error handling. The main gap is the lack of output format explanation (e.g., what the tool returns - image URL, base64, etc.), which is important since there's no output schema.

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

  Parameters4/5

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

  Schema description coverage is 100%, so the baseline is 3. The description adds significant value by explaining parameter purposes beyond the schema: it clarifies that prompt is required, endpoint_id is recommended over model for permission reasons, model has specific version differences, size has resolution requirements, and image_url/ref_image_urls enable specific generation modes. It also notes the watermark parameter (present in schema but not mentioned in description) is a minor gap.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: '使用豆包 Seedream 模型生成图片' (use Doubao Seedream model to generate images). It specifies three distinct functions (text-to-image, image-to-image, multi-image fusion) and distinguishes itself from sibling tools (generate_video, query_video_task) by focusing on image generation rather than video.

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

  Usage Guidelines4/5

  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 different parameters (e.g., image_url for image-to-image, ref_image_urls for multi-image fusion). It mentions an alternative approach (using endpoint_id vs. model name) and includes troubleshooting guidance for errors. However, it doesn't explicitly state when NOT to use this tool versus sibling tools or other alternatives.

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

• query_video_taskA
  4.6/5.0
  Behavior4/5

  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 successfully explains the asynchronous nature of video generation and documents the four possible task states (pending, processing, success, failed) with their meanings. It also mentions that successful results include video download URLs. However, it doesn't cover potential error conditions beyond 'failed' state or rate limits.

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

  Conciseness5/5

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

  The description is well-structured and appropriately sized. It starts with the core purpose, explains the usage context, documents the task states, provides parameter guidance, and describes return values - all in a compact format with zero wasted sentences.

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

  Completeness4/5

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

  For a single-parameter query tool with no output schema, the description provides excellent coverage of purpose, usage context, behavioral details, and return values. The only minor gap is the lack of explicit error handling details beyond the 'failed' state, but overall it's highly complete for this tool's complexity.

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

  Parameters4/5

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

  With 100% schema description coverage, the schema already documents the single required 'task_id' parameter. The description adds value by specifying that task IDs come from 'generate_video' returns, providing important contextual information about parameter sourcing that isn't in the schema.

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

  Purpose5/5

  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 '查询豆包视频生成任务的状态和结果' (query Doubao video generation task status and results), which is a specific verb+resource combination. It distinguishes itself from sibling tools 'generate_image' and 'generate_video' by focusing on querying existing tasks rather than creating new content.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use this tool: '视频生成是异步任务，需要使用此工具查询任务状态' (video generation is an asynchronous task, you need to use this tool to query task status). It also references the sibling tool 'generate_video' as the source of task IDs, providing clear context about the workflow.

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