Server Quality Checklist

Tool Scores

• lingie_run_statusA
  4/5.0
  Behavior4/5

  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 clearly discloses a read-only, no-download behavior ('只查询，不下载输出文件') and states what information is returned (status, progress, output list). This is strong behavioral transparency for a simple query tool, though it does not cover error cases or rate limits.

  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, front-loaded sentence that states the purpose and the key behavioral qualifier with no redundancy. Every word contributes to understanding the tool.

  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 one-parameter query tool with complete schema coverage, the description covers the purpose, read-only nature, and the scope of returned data. It could be more explicit about the return format, but the description is largely complete for making the correct call.

  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 100%, and the run_id parameter is already documented as the run_id returned by lingie_run_workflow. The description adds no additional meaning beyond what the schema provides, so the baseline of 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 declares a specific verb '查询' (query) and precisely defines the object: the current status, progress, and output list of a Lingji generation task identified by run_id. It also differentiates itself from siblings by explicitly stating it does not download output files, which distinguishes it from lingie_run_result.

  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?

  Usage context is implied: the run_id is described as coming from lingie_run_workflow, and the description clarifies this tool is query-only and does not download files. However, it does not explicitly name alternatives or state when-not-to-use it (e.g., if downloads are needed, use lingie_run_result instead).

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

• lingie_upload_fileA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses the core effect (uploading to ComfyUI input directory) and the return value (filename), which is critical for downstream use. However, it does not disclose edge behaviors like overwrite policy, file-type validation, size limits, or whether directories are created.

  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?

  Two concise sentences with no filler. The action is stated immediately, followed by the practical downstream guidance about using the returned filename. 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 low-complexity tool with 2 params and no output schema, the description adequately covers the essential context: what is uploaded, where, and how the result is consumed. It does not promise optional behavior or leave critical return information unexplained. A small gap is the lack of mention of potential failures or prerequisites like ComfyUI availability.

  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 100%, so the schema already documents both file_path and filename. The description adds mild value by restricting file types to images/video/audio, which is not present in the schema, but it does not otherwise enrich the parameter meanings.

  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 names a specific verb (上传/upload), a precise resource (local files to ComfyUI input directory), and states the intended use cases (image-to-image, reference image, first frame). It is clearly distinguishable from all siblings, none of which perform file upload.

  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 explains when this tool is appropriate: before invoking workflows that require local media as input, such as image-to-image or reference-image params. It does not need to state alternatives because no sibling handles upload, though it could have been more explicit about the order of operations relative to lingie_run_workflow.

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

• lingie_healthA
  4.2/5.0
  Behavior3/5

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

  There are no annotations, so the description bears the full burden. It discloses the checks performed (online status, ComfyUI engine, auth) and recommends calling before generation, which implies a safe read-only operation. However, it does not explicitly state that the call has no side effects or describe what the response contains or failure looks like.

  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: it opens with the core purpose, lists the specific checks, and ends with the practical usage recommendation. Every clause adds value, and there is no redundant 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 a zero-parameter health-check tool, the description is largely complete: it states what is checked and when to use it. There is no output schema, so the agent must discover the response format at runtime, but the simplicity of the tool keeps this gap minor.

  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 accepts zero parameters and the input schema is empty, so no parameter documentation is needed. The description adds no parameter details, which is appropriate here; the baseline of 4 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 states a specific verb ('检查' / check) and resource ('灵姬客户端本地 API 的可用性'), and enumerates exactly what is verified: service online, local ComfyUI running, auth required. This clearly distinguishes it from siblings that list workflows, run workflows, or manage runs.

  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 usage context: '开始生成前建议先调用' (recommended to call before starting generation). It does not mention when not to use it or alternatives, but no alternative is relevant for a health-check tool, so the guidance is clear enough.

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

• lingie_list_workflowsA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. '列出' and the return fields imply a read-only discovery operation, and the two-step note prevents confusing it with execution, but it does not mention any limits, auth expectations, or pagination.

  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?

  Two concise sentences deliver purpose, output fields, and follow-up workflow. No filler or redundancy, and the most important information 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 zero-parameter list tool with no output schema, the description provides the purpose, output fields, and next steps, which is enough to invoke and interpret it. It stops short of explaining potential edge cases or response variations, but those are not necessary for correct usage here.

  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 no parameters and 100% schema coverage, so there is nothing to document. The description correctly focuses on output and follow-up tools rather than inventing parameter guidance.

  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 verb and resource ('列出...工作流') and immediately scopes it to available generation types. It also names the return fields (id, name, category, free), which distinguishes it from parameter-inspection and submission tools.

  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 clearly places the tool in a workflow: use workflow_capabilities to inspect parameters and run_workflow to submit. This tells the agent where list_workflows fits, though it does not explicitly state exclusion cases or when to prefer a sibling.

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

• lingie_run_resultA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description bears the behavioral disclosure burden. It discloses the key side effect: when the task is complete, output files are downloaded locally and a file-path list is returned. It does not mention repeated-call behavior or error semantics, but the main non-obvious behavior is surfaced.

  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, front-loaded with the action and resource, then the conditional result behavior, then the usage context. There is no filler or redundant restatement.

  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?

  With only one parameter and no output schema, the definition covers the main states (running vs completed), the delivered artifact (file paths), and the intended workflow position. It could add an explicit note about how it differs from lingie_run_status, but that is a minor gap given the tool's low 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?

  Schema coverage is 100%, and the schema already explains that run_id is the value returned by lingie_run_workflow. The description only mentions run_id in passing and adds no extra semantic detail beyond the schema, so the baseline 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 states a specific verb-resource pair: query a generation task by run_id and retrieve its result. It clearly separates the two conditional behaviors—status/progress while generating versus downloading output files and returning paths on completion—which distinguishes it from the status-only sibling lingie_run_status.

  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 explicitly says it is meant to be used with polling after lingie_run_workflow times out, giving concrete context for when to call it. It does not explicitly contrast it with lingie_run_status, but the intended usage position is clear enough.

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

• lingie_workflow_capabilitiesA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. The verb '查看' indicates a read-only lookup, and the phrase 'before submitting lingie_run_workflow' clarifies it does not execute the workflow. It does not explicitly state 'no side effects' or mention permissions, but the wording is sufficient for a safe introspection 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?

  Two concise sentences with no filler. The first sentence front-loads the purpose and output contents; the second sentence gives the critical usage trigger. Every phrase earns its place.

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

  Completeness5/5

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

  For a single-parameter introspection tool with no output schema, the description is complete: it states exactly what information is returned, references the prerequisite relationship with lingie_run_workflow, and the schema supplies the input source. Nothing critical is missing for an agent to call it correctly.

  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 covers 100% of parameters and already describes workflow_id as coming from lingie_list_workflows, so the baseline is 3. The description adds no extra semantic nuance about the input parameter; its mentions of names, types, etc. refer to the output content, not the input.

  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 ('查看' / view) and a specific resource ('指定工作流的参数模式' / specified workflow's parameter schema), and enumerates exactly what information is returned (name, type, required, default, enum values, submission method). It also positions itself as a prerequisite to lingie_run_workflow, which clearly distinguishes it from the sibling execution and status tools.

  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 explicitly states when to call it: '提交 lingie_run_workflow 前务必先调用本工具' (must call this tool before submitting lingie_run_workflow) to understand how to fill params. This gives clear, actionable usage context, though it does not mention when not to use it or name alternative tools.

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

• lingie_cancel_runA
  4.4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals a critical non-obvious behavior: the engine executes one task at a time, and canceling may interrupt the currently running task rather than the requested one. This is exactly the kind of side-effect transparency an agent needs.

  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 short, direct, and front-loads the purpose. Every clause adds value: the action, the engine limitation, the possible mismatch between run_id and the affected task, and the confirmation requirement. No unnecessary 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 a single-parameter cancellation tool, the description covers the most important contextual risk and explains why caution is needed. It does not describe return behavior or error cases, but the operation is simple enough that the core context is largely 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?

  Schema description coverage is 100%, with run_id documented as '要取消的 run_id'. The tool description adds no additional parameter format or value constraints, but the schema already provides sufficient meaning, so the baseline score of 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 a specific action, '取消' (cancel), on a specific resource, a Lingji generation task. It is immediately distinguishable from sibling tools like run_status or run_workflow, and the warning emphasizes the real effect of the operation.

  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 usage context: cancellation is global to the local ComfyUI engine and may affect a different task than the specified run_id. It explicitly tells the agent to confirm before calling, which is strong guidance, though it doesn't enumerate exact when-to-use vs. when-not-to-use scenarios.

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

• lingie_run_workflowA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and meets it. It discloses the default blocking wait, ~20-second auto-degradation to run_id, ~30-second MCP host timeout, background continuation, and the side effect that canceling interrupts the local engine's current task.

  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?

  Three dense sentences cover submission, waiting, timeout degradation, background continuation, immediate mode, and cancellation. The core action is front-loaded and every sentence earns its place.

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

  Completeness5/5

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

  For a complex async execution tool with no annotations, this description is complete: it tells the agent what results to expect, when to fall back, how to avoid losing results to timeouts, and how to cancel. The absence of an output schema is compensated by explicitly stating that local output paths or a run_id are returned.

  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 100%, so the baseline is 3. The description adds value by explaining wait semantics beyond the schema, mentioning LINGIE_MCP_MAX_BLOCK_MS tuning, and tying params to lingie_workflow_capabilities parameter names with submission_hint formats.

  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 and resource: executing a workflow in the local ComfyUI engine. It also distinguishes itself from siblings by contrasting submission behavior with lingie_run_result polling and lingie_cancel_run cancellation.

  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 explicitly explains when to use this tool and when to use alternatives: submit with run_workflow, poll with lingie_run_result after background degradation, cancel with lingie_cancel_run. It also covers the wait=false immediate-return mode.

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