Server Quality Checklist

Tool Scores

• build_seedance_promptB
  3.1/5.0
  Behavior3/5

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

  Annotations already cover safety (readOnlyHint, destructiveHint, idempotentHint). The description adds that the output is deterministic and highlights language and structural features, but does not disclose operational behavior such as authentication needs, rate limits, or error handling. Since annotations carry the safety profile, the description adds moderate value but no deep behavioral detail.

  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, dense sentence that front-loads the main verb and resource, then lists key features efficiently. It contains no filler and communicates the tool's purpose clearly in a compact form, even though it omits context.

  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 11 parameters, no output schema, and no description of return values, the tool is under-specified. There is no mention of the expected output format (e.g., a string), any specific workflows it belongs to, or how it relates to sibling tools. The description gives a high-level summary but lacks the operational and contextual detail an agent needs for correct use.

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

  Parameters1/5

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

  The schema has 11 parameters with 0% description coverage, and the description provides almost no parameter-level meaning. It merely implies that 'subject and camera motion' and 'reference bindings' exist as parameters, but does not explain their constraints, formats, or relationships. The description fails to compensate for the lack of schema documentation, leaving an agent without the information needed to populate parameters correctly.

  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 action ('Turn a rough idea into a deterministic prompt') and identifies the resource (video prompt) with key attributes (English or Chinese, separate subject/camera motion, reference bindings, continuity controls). It distinguishes itself from siblings by the core action of building a prompt versus planning, diagnosing, or fetching resources.

  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 siblings like 'diagnose_seedance_prompt' or 'plan_reference_sequence'. There is no mention of prerequisites, conditions, or exclusions. An agent would have to infer usage from the name alone, without explicit context.

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

• get_see_dance_2_resourcesB
  3.4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety/closed-world profile is covered by structured data. The description adds genuinely useful behavior beyond that: 'without fetching external content' tells the agent this tool performs no network/outside lookups. However, it doesn't disclose what the returned 'resource' actually looks like (text? URL? structured template?), which matters since no output schema exists.

  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?

  A single 16-word sentence with zero waste. The action and resource scope are front-loaded, and the behavioral qualifier ('without fetching external content') is appended at the end. Every word earns its place and nothing is redundant.

  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 dead-simple tool (one optional parameter with an enum, strong read-only annotations, closed world), the description covers resource categories and the no-fetch behavior sufficiently. The main remaining gap is return-value format, which is left to the agent's inference since no output schema exists — a minor shortfall for such a simple tool.

  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%, and the enum values (all, prompting, workflows, references, safety) have no per-value explanations. The description partially compensates by naming the four resource categories in its prose, which maps roughly to the enum, but it never spells out what each topic value returns and never clarifies what 'all' bundles together. Meaning is added but the compensation is incomplete.

  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 ('Return') and resource ('canonical See Dance 2 prompting, workflow, reference, or safety resources'), and enumerates the four resource categories. The qualifier 'without fetching external content' adds a meaningful scope note that separates this from content-fetching tools. It doesn't explicitly name sibling tools, but the action (return resources vs build/plan/diagnose) differentiates it clearly enough.

  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 gives no when-to-use guidance, exclusions, or explicit routing to alternatives. Siblings (build_seedance_prompt, plan_reference_sequence, diagnose_seedance_prompt) all involve creating or analyzing prompts, and this tool returns resources — but this contrast is only implied, never stated. No conditions describe when an agent should pick this tool over a sibling.

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

• diagnose_seedance_promptA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds what aspects it checks, which is useful context. However, it does not disclose the output format or any potential side effects (though read-only implies none). Given the annotations, the description adds some value but not deep behavioral context, so a 3 is appropriate.

  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 verb and lists the checked aspects. There is no fluff or repetition, and every word contributes to clarity. It is appropriately concise for a single-purpose diagnostic tool.

  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?

  The tool has no output schema, so the description must explain what the agent can expect as a result. It only lists what is checked, not what the output will be (e.g., a score, list of issues, or pass/fail). An agent cannot know how to interpret the result or take subsequent actions. This is a significant gap for a diagnostic tool, making the description incomplete.

  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 has 0% coverage for the single 'prompt' parameter, so the description must compensate. It does mention that prompts can be in English or Chinese, which gives some language guidance, but it does not explain expected format, structure, or provide examples. This is marginal compensation for the missing schema coverage, and the parameter is simple enough that a 3 is fair.

  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 identifies the exact resource (English or Chinese prompts) and the specific aspects examined (motion, camera direction, lighting, continuity, preserved reference tokens). This clearly differentiates it from siblings like build_seedance_prompt (which constructs prompts) and plan_reference_sequence (which plans sequences). The purpose is unambiguous and distinct.

  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 when to use the tool (when you need to diagnose/check a Seedance prompt) but does not explicitly mention alternatives or provide exclusions. It does not state 'use this instead of X' or specify conditions when it should not be used. The sibling names suggest a workflow, but the description fails to route the agent explicitly.

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

• plan_reference_sequenceA
  3.7/5.0
  Behavior4/5

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

  Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is clear. The description adds the behavioral trait 'deterministic', which is not present in annotations and is valuable for an agent relying on reproducibility. It does not contradict annotations and provides a genuine extra behavioral guarantee, so a score of 4 is warranted.

  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 ('create a deterministic 1–6 shot sequence') and then lists key attributes. No waste, no repetition, and it is immediately scannable. This is an exemplary concise description.

  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 has 6 parameters, no output schema, and no property descriptions. The description captures the essential output (a sequence) and key concepts, but it does not explain what exactly the output looks like (e.g., a plan object), nor does it clarify how the required 'idea' feeds into planning. Sibling tools suggest a broader workflow, and without output schema, an agent lacks information about the return format. While annotations cover safety, the description leaves meaningful gaps in usage context, so completeness is moderate.

  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?

  Given schema description coverage of 0%, the description carries the full burden of explaining parameters. It alludes to 'reference bindings' (mapping to referenceBindings), 'timing' (shotCount and totalDurationSeconds), and 'continuity anchors' (continuityAnchor), but it does not clarify the role of 'idea' (a required parameter) or 'cameraStyle'. The description offers some semantic hints but leaves key parameters unexplained, so it only partially compensates for the schema's lack of descriptions.

  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: to create a deterministic 1–6 shot sequence with explicit reference bindings, timing, continuity anchors, and end frames. The verb 'create' and resource 'sequence' are specific, and the mention of 'deterministic' and the shot range differentiates it from sibling tools like build_seedance_prompt (which likely focuses on prompt construction) and diagnose_seedance_prompt (which is for diagnostics). The purpose is unambiguous and well-scoped.

  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 its siblings. It does not mention prerequisites, typical use cases, or conditions that would warrant selecting an alternative. An agent is left to infer that 'plan' implies a pre-build step, but there is no explicit direction or exclusion, so usage guidance is largely absent.

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