Server Quality Checklist

Tool Scores

• list_generation_tasksA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the behavioral transparency burden. It adds useful context about ordering (reverse chronological) and scope (current API Key user), but it omits pagination behavior, response format, and any rate-limit or authentication considerations.

  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, front-loaded sentence that clearly states the action, resource, and ordering. It includes the endpoint reference without unnecessary fluff, making it highly concise and effective.

  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 list tool with all optional parameters and no output schema, the description provides the essential context: scope, ordering, and endpoint. However, it could be slightly more complete by mentioning what fields are included in each returned task, though this is not critical.

  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 input schema already provides descriptions for all three parameters (page, status, pageSize) including defaults, minimums/maximums, and an enum. The description adds no additional parameter-level meaning, so the baseline of 3 applies.

  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 uses a specific verb '返回' (return) and resource '当前 API Key 用户的图片生成任务列表', and it specifies the ordering as '按创建时间倒序' (reverse chronological). This clearly distinguishes it from the sibling tool get_generation_task, which retrieves a single task.

  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?

  No explicit when-to-use or alternative guidance is provided, but the scope ('current API Key user') and endpoint mapping make the listing purpose clear. The distinction from the singular get_generation_task is implied by the plural 'tasks' but not explicitly stated.

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

• get_generation_taskA
  4/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It discloses the key success behavior (images field becomes an array of public links) and provides the API endpoint. However, it does not mention error handling, failure states, or authentication requirements, leaving gaps in behavioral expectations for a plain status query.

  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, front-loaded with purpose, and includes an API endpoint that provides additional mapping without redundancy. Every word earns its place; there is no filler or tautology.

  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 single-parameter task with no output schema or annotations, the description is fairly complete: it explains the purpose, the success output (images array of public links), and the endpoint. It lacks error behavior and response details beyond success, but given the tool's simplicity and the sibling context, the core information is sufficiently covered.

  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 coverage is 0% for the single parameter taskId. The description indirectly explains it through the endpoint path 'GET /openapi/v1/images/generation/tasks/{taskId}', implying taskId is the task identifier. However, it does not explicitly state the parameter's origin, required format, or how to obtain it, so compensation is partial.

  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 action: '查询图片生成任务状态' (query image generation task status). It specifies the resource (image generation task) and the scope (status check), and it distinguishes itself from siblings by mapping directly to the GET endpoint for a single task, unlike list_generation_tasks or generate_image.

  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 that this tool is for checking task status, and reveals the success condition (images field contains downloadable links). However, it does not explicitly state when not to use this tool or mention alternatives such as wait_for_generation_task for polling, so it lacks exclusions.

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

• estimate_creditsA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses non-mutating behavior (no image generation, no credit deduction) and synchronous execution, along with the API endpoint. However, it omits error behavior, return format, and authentication requirements.

  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 compact, consisting of two sentences. It front-loads the purpose, then states side effects and the corresponding endpoint, with no redundant information.

  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 description covers core behavior and side effects, but the mismatch between the empty schema and the implied parameters creates ambiguity. It lacks details on return structure, error handling, and parameter passing, making it less complete for actual invocation.

  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 input schema is empty, so the description is the only source of parameter information. It lists provider, model, size, and aspect ratio, but does not specify types, requiredness, or how these parameters are passed (e.g., in body or query). This partial information is helpful but incomplete.

  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 estimates credits required for image generation using parameters like provider, model, size, and aspect ratio. It explicitly differentiates itself from sibling tools like generate_image by noting it does not actually generate images or deduct credits.

  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 implicitly positions the tool as a pre-generation cost estimator by stating it returns synchronously and does not generate or deduct credits. It does not explicitly name alternatives or provide exclusion criteria, but the context makes the intended usage clear.

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

• generate_image_asyncA
  4.2/5.0
  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 non-blocking behavior, immediate taskId return, and that successful tasks yield public links. However, it does not mention failure scenarios, credit consumption, or rate limits, leaving significant behavioral gaps for a creation tool.

  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 concise and front-loaded. The first sentence explains the core async behavior, the second adds follow-up actions, and the final sentence gives use cases and API endpoint. Every sentence earns its place without fluff.

  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 async complexity and lack of annotations/output schema, the description covers the essential lifecycle: create task, get taskId, query/wait, and result as public link. It lacks details on failure handling or credit implications, but these may be covered by sibling tools like get_generation_task. Overall, it is reasonably complete for an entry-point tool.

  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?

  The input schema has zero parameters, so the baseline is 4. The description does not need to explain parameter syntax and appropriately focuses on workflow rather than parameter details.

  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 creates an image generation task and immediately returns a taskId without blocking. This verb+resource description distinguishes it from sibling generate_image (likely synchronous) by highlighting the asynchronous nature.

  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 usage context: '适合大图、批量生成' indicates when to use async mode. It also directs to get_generation_task and wait_for_generation_task for follow-up, but does not explicitly mention when to prefer the synchronous generate_image sibling.

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

• get_subscriptionA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It signals a read-only operation via '获取' and the explicit 'GET' endpoint, and it discloses the output scope (account subscription, credits, freeUsages, reset time). However, it does not explicitly state side-effect-free behavior, rate limits, or whether the call consumes credits.

  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 packs all essential information: resource, returned fields, account scope, and endpoint. No wasted words or repetition.

  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 parameterless read-only tool with no output schema, the description is largely complete: it names the endpoint and enumerates the key response components. It could be more complete by describing the shape/nesting of freeUsages or reset time, but given the tool's simplicity, this is a minor gap.

  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?

  The tool has zero parameters, so the schema is trivially 100% covered. Per baseline guidance, 0 params receives a 4. The description adds value by explaining what the response contains, which is helpful even though there is nothing to configure for invocation.

  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 uses a specific verb ('获取') with a clear resource ('订阅信息与积分余额') and includes the exact fields returned: subscription status, available credits (monthly/permanent/limited-time), freeUsages, and reset time. It also names the corresponding GET endpoint, making the tool's purpose unmistakable and distinct from the image generation siblings.

  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 clearly implies the tool is used to check current account subscription and credit balance, but it does not explicitly state when to use it versus alternatives like estimate_credits, nor does it mention any exclusions or prerequisites. This leaves usage context implicit rather than explicit.

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

• wait_for_generation_taskA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses that the tool polls and waits for completion, returns a link or failure reason, and is a convenience wrapper to avoid manual polling. It does not explicitly describe timeout behavior, but the schema's timeoutSeconds parameter and the return of failure reasons provide reasonable coverage.

  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, then adds the usage context. Every clause earns its place with no redundancy or 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?

  Given the tool's moderate complexity (3 params, no output schema), the description provides the essential return type (public link or failure reason), the polling nature, and the intended call pattern after generate_image_async. It does not detail edge cases like timeout or invalid task IDs, but those are partially inferable from the schema and sibling context.

  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 67% (pollIntervalMs and timeoutSeconds have descriptions; taskId is self-explanatory). The description adds no parameter-specific information beyond suggesting the tool avoids manual polling. This is adequate but not exceptional, so baseline 3 is appropriate.

  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 'poll wait' (轮询等待) and the resource 'async generation task' (异步生成任务), and specifies it returns public image link or failure reason. It distinguishes itself from siblings like get_generation_task by explicitly mentioning it is meant to be called after generate_image_async and avoids manual polling.

  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 explicit context: '适合在 generate_image_async 之后直接调用，避免手动多次轮询' (suitable for direct call after generate_image_async, avoiding manual polling). It clearly states when to use it and the benefit, but does not explicitly name alternatives or exclusion conditions.

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

• generate_imageA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses key behaviors: synchronous execution, direct return of base64 data and metadata, support for multiple models, and a warning about high return volume. It does not cover errors or authentication, but the provided details are substantial and useful.

  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 compact and well-structured: a single sentence covering core functionality, followed by a short warning about async alternatives. Every clause adds value, and the critical distinction (synchronous vs async) is front-loaded.

  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 tool with no output schema, the description covers the return value (base64 data and metadata), supported models, reference image support, and the API endpoint. It misses explicit parameter names for model selection and error handling, but overall it is fairly complete for invocation.

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

  Parameters5/5

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

  The input schema has zero parameters, so the description is the only source of parameter info. It explicitly mentions 'fileUri 或 base64 inlineData' for reference images and lists supported models, adding meaning beyond the empty schema. Given the 0-param baseline of 4, this extra detail qualifies for a 5.

  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 '同步生成图片，直接返回 base64 图片数据与生成元数据' clearly defining the tool's function. It differentiates from sibling 'generate_image_async' by emphasizing the synchronous nature and explicitly warns about large payloads, naming the alternative.

  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 provides explicit when-to-use guidance: use this for synchronous generation and switch to generate_image_async for 4K images due to large return volume. It also mentions support for reference images, indicating use cases like image-to-image and editing.

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