Server Quality Checklist

Tool Scores

• plan_reference_sequenceB
  3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds the 'deterministic' trait and outlines the plan components, which are useful behavioral details beyond the annotations. However, it does not describe what the output looks like or how the plan is structured, leaving some behavioral ambiguity.

  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 sentence that front-loads the core action and scope. Every word contributes: it specifies the deterministic nature, the 1–6 shot range, and the key components. There is no redundancy or filler, making it highly efficient.

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

  Completeness2/5

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

  With six parameters, no output schema, and zero parameter descriptions, the tool demands substantial contextual guidance. The description only gives a high-level overview and uses jargon like 'reference-aware' and 'continuity anchors' without elaboration. An agent lacks sufficient information to correctly populate parameters or interpret the result, making the definition incomplete.

  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 description coverage is 0%, so the description is the sole source for parameter meaning. It loosely references 'reference roles', 'timing', 'continuity anchors', and 'intended end frames', which map partially to referenceRoles, shotCount/totalDuration, and continuityAnchor, but it does not explicitly explain each parameter's format, defaults, or constraints. The agent must infer mapping from the vague terms.

  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 clear verb ('Create') and resource ('deterministic 1–6 shot sequence'), with specific components like reference roles and continuity anchors. It is unambiguous about the task. However, it does not explicitly differentiate from sibling tools like build_video_prompt or diagnose_video_prompt, though the planning focus is distinct enough to infer.

  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?

  The description provides no guidance on when to use this tool versus alternatives. It only states what it does, leaving the agent to infer that planning is needed. There is no mention of excluded scenarios or conditions that would favor a sibling tool, so the agent receives no decision-support.

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

• build_video_promptB
  3.2/5.0
  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, covering the operational safety profile. The description adds context by noting the output is 'deterministic' and includes specific elements, which aligns with idempotency and read-only behavior. However, it does not disclose any limitations, edge cases, or additional behavioral nuances beyond the annotations, so it adds modest value but not rich disclosure.

  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, well-structured sentence that front-loads the core purpose and lists the included elements without redundancy or filler. Every word contributes to conveying the tool's function, making it highly concise and appropriately sized.

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

  Completeness2/5

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

  Given the tool's complexity (11 parameters, enums, no output schema), the description is incomplete. It does not explain when to use it, what the output structure looks like, or how parameters interact. The agent has little guidance on how to choose parameter values or what to expect from the result. The description covers high-level intent but lacks the depth needed for correct invocation in varied scenarios.

  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 schema description coverage at 0%, the description must compensate for parameter understanding. It lists several key parameters (motion, camera, lighting, reference roles) and implies continuity controls, giving some semantic meaning. However, it omits many other parameters like workflow, aspectRatio, outputLanguage, durationSeconds, and negativeConstraints, and does not explain their purpose or constraints. The description adds value but only partially compensates for the total lack of schema descriptions.

  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 clearly states the tool's function: turning a rough idea into a deterministic prompt pack with specific elements (motion, camera, lighting, etc.) and language options. It is specific about the output resource and purpose, but does not explicitly differentiate from sibling tools like plan_reference_sequence or diagnose_video_prompt, so it loses a point for lack of sibling distinction.

  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?

  The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or contexts where another sibling would be more appropriate. The only hint is that it 'turns a rough idea into a prompt pack,' implying it's for prompt creation, but no explicit when/when-not guidance is given.

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

• diagnose_video_promptA
  3.9/5.0
  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 agent knows this is a safe, non-mutating operation. The description adds the scope of the check (specific quality dimensions) but does not disclose output format or what happens when issues are found. Given the annotations cover the safety profile, the description adds moderate context but stops short of full 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.

  Conciseness5/5

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

  The description is a single, tight sentence. It opens with the action verb 'Check' and immediately lists the subjects and aspects, leaving no room for fluff. Every word contributes to the meaning, making it highly efficient and easy to parse.

  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 a one-parameter read-only tool, the description covers the input well but says nothing about the output or what constitutes a 'diagnosis'. With no output schema, an agent might wonder whether the tool returns a report, a pass/fail, or a list of issues. This is a notable gap, though the tool's simplicity mitigates it. A sentence on the return value would round it out.

  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 compensate. It does so by clarifying that the 'prompt' parameter is expected to be a video prompt and that it can be in English or Chinese. It also enumerates what the tool evaluates in that prompt. This provides meaning beyond the schema's bare string type and length constraints, helping the agent supply an appropriate value.

  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 starts with a specific verb 'Check' and names the resource 'English or Chinese prompts', then lists the exact dimensions checked (scene, motion, camera, lighting, continuity, reference tokens). This clearly differentiates it from siblings like build_video_prompt (which constructs prompts) and plan_reference_sequence (which plans a sequence). An agent could easily infer this is a diagnostic tool.

  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 implies this tool is used to evaluate the quality of a video prompt, but it does not explicitly state when to use it versus the alternatives. It offers no conditions like 'use after building a prompt' or 'use to validate before submitting'. Usage guidance is implied by the verb 'Check' but not made explicit.

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

• get_seevido_resourcesA
  4/5.0
  Behavior4/5

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

  Annotations already cover read-only and idempotent behavior. The description adds a valuable non-annotation detail: 'without fetching external content', indicating a local static lookup. No contradiction with 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?

  Single sentence, no unnecessary words, front-loads the core action and scope. Efficient and well-structured.

  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 tool with one optional parameter and no output schema, the description sufficiently covers the main behavior. It doesn't specify the return format, but given the simplicity and that safety/read-only annotations are present, it's adequate.

  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 partially compensates by listing the resource categories ('prompting, workflow, model-orientation, or safety') which map directly to the topic enum values. It adds context about what topics filter, though it doesn't explicitly explain the parameter's effect.

  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 ('Return') and resource type ('canonical SeeVido prompting, workflow, model-orientation, or safety resources') with a distinguishing constraint ('without fetching external content'). Clearly differentiates from siblings like build_video_prompt which focus on creation rather than retrieval.

  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?

  Implies usage for obtaining standard SeeVido resources but does not explicitly state when to use this tool versus alternatives like build_video_prompt or plan_reference_sequence. No exclusions or comparative guidance are provided.

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