Server Quality Checklist

Tool Scores

• diagnose_video_promptB
  3.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the language scope (English/Chinese) and the specific checks performed. However, it does not disclose what happens on malformed input or what the result looks like, leaving some behavioral detail unspecified.

  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?

  A single, tight sentence with no filler. The diagnostics are listed immediately after the verb, front-loading the core behavior. Nothing extraneous.

  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?

  Complexity is low (one parameter, no output schema), and the description covers the input well. However, it omits the result contract: an agent cannot tell whether the tool returns a pass/fail verdict, a scored report, or a corrected prompt. For a diagnostic tool, some statement of expected output would be valuable.

  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 must carry the semantic weight for the 'prompt' parameter. It compensates well: it clarifies that the prompt is an English or Chinese video-generation prompt and enumerates the properties it should contain (scene, motion, camera, lighting, continuity, reference tokens). This adds real meaning beyond the bare string schema.

  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 ('Check') with a clear resource (an English or Chinese video prompt) and enumerates the exact diagnostic dimensions checked: scene readability, visible motion, camera direction, lighting, continuity controls, and preserved reference tokens. The diagnosing role is implicitly distinguishable from siblings build/plan/get.

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

  Usage Guidelines2/5

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

  No guidance on when to use this tool versus alternatives. With siblings like build_video_prompt, an agent is not told 'use this to validate before building' or any when-not conditions. The description offers no context for selection.

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

• plan_reference_shotsA
  3.5/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds 'Read-only and deterministic', which is largely redundant with the annotations but does explicitly mention determinism. It provides no additional behavioral details about output structure or side effects, so only modest value is added beyond the annotations.

  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 a single, focused sentence that front-loads the core purpose and key output attributes. Every phrase adds value, with no filler or redundancy. It is appropriately concise for a tool with a straightforward function.

  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?

  While the purpose is clear and safety is covered by annotations, the description does not explain how the output is structured (e.g., what 'end frames' or 'continuity anchors' look like in practice) or provide guidance on how each parameter affects the result. For an agent to call the tool correctly, it may need more detail on parameter semantics and expected outputs, especially given the lack of an output schema and zero schema descriptions.

  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 must compensate. It explicitly names 'reference roles', 'camera direction', and 'continuity anchors', which map to referenceRoles, cameraStyle, and continuityAnchor, and '1 to 6 timed shots' implies shotCount and totalDurationSeconds ranges. However, it does not discuss the exact syntax, defaults, or interactions of parameters, leaving room for ambiguity. It partially compensates but not fully.

  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 states a specific verb ('Break'), a resource ('one video idea'), and the output format ('1 to 6 timed shots') with explicit elements (reference roles, camera direction, end frames, continuity anchors). It clearly distinguishes this tool from siblings by focusing on shot planning with references, whereas siblings handle diagnosis, building prompts, or resource retrieval.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus the sibling tools (diagnose_video_prompt, build_video_prompt, get_china_video_resources). The description only states what the tool does, not when it should be selected or what alternatives exist. This leaves the agent to infer usage context on its own.

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

• build_video_promptA
  3.9/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by stating it does not generate video and that the output is 'deterministic', giving insight into behavior beyond the annotations. It does not contradict the annotations and provides useful context about the tool's nature.

  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 two sentences with zero waste. The first sentence front-loads the core purpose and scope, and the second sentence delivers an important caution. Every word earns its place.

  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?

  Given 11 parameters, no output schema, and no parameter documentation in the schema, the description is too sparse. It explains the high-level purpose and some controls but omits the output structure, China-specific context (despite the title), and details on key parameters like workflow and duration. It is adequate for orientation but not fully complete for a tool of this complexity.

  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?

  With 0% schema description coverage, the description must compensate. It mentions motion, camera, lighting, reference, and continuity controls, which map to several parameters (motion, camera, lighting, referenceConstraints), and 'English or Chinese' hints at outputLanguage. However, it does not explain workflow, aspectRatio, durationSeconds, negativeConstraints, style, or idea, leaving many parameters unexplained.

  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 verb 'Turn' and the resource 'a rough idea into a deterministic English or Chinese prompt pack', listing the control domains (motion, camera, lighting, reference, continuity). The explicit negation 'This does not generate video' distinguishes it from video generation tools and positions it against siblings like diagnose_video_prompt, which likely analyzes prompts.

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

  Usage Guidelines3/5

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

  The description gives a clear negative constraint ('does not generate video') but offers no explicit alternatives or conditions for when to use this tool versus siblings like plan_reference_shots or get_china_video_resources. It implies usage (when you have a rough idea) but does not name or contrast with related tools.

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

• get_china_video_resourcesA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds the behavioral detail that it does not fetch external content, which clarifies that the data is canonical and local. This adds value beyond the annotations, though it doesn't describe the output format.

  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 two concise sentences that front-load the core purpose and add a key behavioral note. There is no fluff or redundant information.

  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 simple read-only tool with one optional parameter and no output schema, the description is mostly complete. It states what it returns and that it does not fetch external content, but it does not specify the format of the resources (e.g., URLs, text). Given the low complexity, this is acceptable but not exhaustive.

  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?

  The schema provides a single 'topic' parameter with an enum, so the valid values are already defined. The description lists similar terms (prompting, workflow, etc.) but does not elaborate on the meaning or default behavior. With 0% schema description coverage, the description could compensate but only minimally does.

  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 returns canonical resources from ChinaVideoAI.com covering prompting, workflows, models, and safety. The verb 'return' and the specific resource categories distinguish it from sibling tools like diagnose_video_prompt or build_video_prompt, which focus on prompt creation and diagnosis.

  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 gives clear context: it returns resources, implying use when you need canonical resources. However, it does not explicitly mention alternatives or when not to use this tool. The sibling names make the distinction obvious, but no explicit guidance is provided.

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