Server Quality Checklist

Tool Scores

• query_videoA
  3.7/5.0
  Behavior3/5

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

  No annotations are present, so the description must carry behavioral disclosure. It does convey the core behavior: a task query that returns status/progress and video_url only when completed, implying asynchronous polling. It stops short of describing auth requirements, failure/error states, or whether the operation is safe/read-only.

  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 two short sentences (English + Chinese) with no filler and the main result statement first. The Chinese sentence earns its place by adding the poll-after-create usage context, though it is slightly redundant with 'Query'.

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

  Completeness3/5

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

  The tool is simple, but without an output schema or annotations, the description only partially covers what an agent needs: it gives return fields and the create_video pairing, but not the meaning of api_key/base_url or non-success behavior. This is adequate for happy-path polling but incomplete for robust invocation.

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

  Parameters2/5

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

  Schema has zero description coverage, and the description only mentions video_id ('按 video_id 轮询进度'). It never explains api_key or base_url, which are optional but still part of the invocation surface. Thus the description partially compensates but leaves most parameter semantics to inference.

  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?

  States a specific action ('Query an agnes-video-2.5-flash task') and describes the observable result ('Returns status/progress and video_url when completed'). This clearly differentiates it from sibling tools like create_video or generate_video, which are creation operations rather than polling operations.

  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 Chinese trigger explicitly frames the tool as a poller: '视频创建后，用此工具按 video_id 轮询进度（配合 create_video 使用）', meaning after video creation, poll by video_id in conjunction with create_video. It gives clear when-to-use context but doesn't spell out when not to use it or mention alternative query tools.

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

• create_videoA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden. It discloses the async nature, that it returns video_id and must be polled with query_video, fixed 720P size, seconds range, and limits on images/audios. It does not mention rate limits or error behavior, but the critical async/polling behavior is transparent.

  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 trigger phrases, mode explanations, and examples. It is somewhat long but every section adds value: the Chinese triggers, mode conditions, and examples all serve the agent. Front-loading the async behavior and polling requirement makes key information immediately visible.

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

  Completeness3/5

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

  For an 11-parameter tool with no annotations and no output schema, the description covers the core usage well but leaves gaps. It omits aspect_ratio, seed, api_key, and base_url semantics, and does not document error cases or authentication requirements. The return value (video_id) is stated, and polling is explained, so it is adequate but not fully complete.

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

  Parameters3/5

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

  Since schema description coverage is 0%, the description must compensate. It explains mode, prompt usage, seconds, images, audios, first_frame, and last_frame with concrete examples. However, it does not explain seed, api_key, base_url, or aspect_ratio, which are significant parameters. The aspect_ratio enum values are visible in the schema, but their meaning is not described.

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

  Purpose4/5

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

  The description states a specific verb and resource: 'Create an async agnes-video-2.5-flash task' and notes it returns video_id for polling. It clearly differentiates from query_video by naming it as the polling counterpart. However, it does not distinguish itself from the sibling generate_video, which is also a video-creation tool, so it lacks full sibling differentiation.

  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 explicit trigger phrases (中文触发), recommends async to avoid IDE timeout, and explains when each mode applies: text, keyframe, and reference. It also specifies required inputs per mode (e.g., first_frame/last_frame for keyframe, images/audios for reference). It does not explicitly state when not to use this tool versus generate_video, but the guidance is clear enough for most cases.

  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, the description carries the behavioral burden and covers the return format ('a URL (or base64)'), the local-download side effect when save_path is set, and the different generation modes. It does not discuss latency, cost, or API-key/endpoint configuration, but those omissions are minor for correct invocation.

  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 efficient and front-loaded: purpose, model, and return type first, then triggers, presets, parameter conditions, and two concrete examples. The bilingual trigger list and examples are purposeful rather than filler.

  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 an 8-parameter tool with no output schema, the description covers invocation conditions, parameter behavior, return type, and the optional local side effect with examples. A small gap is the lack of explicit routing to video siblings for video requests, but the tool name and 'image' scope make the boundary clear.

  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 0%, so the description compensates by explaining size tiers, ratio use cases, the images parameter's accepted inputs, and save_path's download behavior. It leaves api_key and base_url semantically unexplained, though those are optional infrastructure parameters and all core generation parameters are well covered.

  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 opens with a concrete action, resource, and model: 'Generate or edit an image with agnes-image-2.5-flash.' It also lists the distinct modes (text-to-image, image-to-image, edit, multi-image compose) and states the return type, making the tool clearly distinguishable from the video-generating siblings.

  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?

  It provides explicit invocation triggers in both Chinese and English and gives a clear decision rule: pass `images` for image-to-image/compose, omit it for pure text-to-image. It does not explicitly mention the video sibling tools as alternatives or include a when-not-to-use section, so the guidance stops short of a full 5.

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

• generate_videoA
  4.4/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states that the tool blocks until completion, may hit client timeouts, supports configurable poll_interval and timeout_seconds, and that on timeout the agent should reuse video_id with query_video. This is substantial and actionable 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.

  Conciseness3/5

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

  The key information is front-loaded and logically organized, but the same guidance is repeated in Chinese and English multiple times. While the bilingual presentation may help some users, it adds redundancy; not every sentence earns its place.

  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 13-parameter tool with no annotations and no output schema, the description covers the essential operational context: when to use it, how it behaves, what to do on timeout, and which alternative to prefer. It does not detail the return value, but the mention of reusing video_id via query_video gives enough follow-up direction.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description needs to compensate. It does explain the two additional parameters poll_interval and timeout_seconds, and it routes all other parameters to create_video via 'Same params as create_video'. However, it does not describe the individual meanings of mode, seed, images, audios, or other fields, relying on a sibling tool's documentation.

  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 opens with a specific action: 'Create a video task and block-poll until completed/failed'. It clearly labels itself as a compatibility tool and distinguishes its synchronous behavior from the preferred async sibling create_video. An agent can immediately tell what this tool does and how it differs from the alternatives.

  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 gives explicit when-to-use and when-not-to-use guidance: it recommends create_video + query_video for general use and reserves generate_video for users explicitly asking for '一步到位 / 直接等视频结果' or 'agnes generate video sync'. This is strong, unambiguous routing to the correct sibling tool.

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