Server Quality Checklist

Tool Scores

• image_batch_editA
  3.7/5.0
  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 of disclosure. It discloses the 20-image limit and independent billing per image, which are important operational traits. However, it does not describe output behavior, whether input files are modified, or any permission 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?

  Two sentences, front-loaded with purpose and then constraints. Every sentence earns its place, with no redundancy or fluff.

  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 no annotations and low schema coverage, the description should cover more ground. It includes key batch limits but omits explanations for most parameters and output handling, making it incomplete for a complex batch operation.

  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 must compensate. It adds meaning to image_paths (max 20, per-image billing) but leaves prompt, size, model, quality, and output_dir unexplained. This is insufficient for a 6-parameter tool.

  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 it executes the same edit instruction on multiple local images one by one, suitable for batch background replacement or uniform style. This specific verb+resource+scope distinguishes it from sibling tools like image_edit (single image) and image_generate.

  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 mentions suitability for batch background replacement or uniform style, providing clear context for when to use the tool. However, it does not explicitly name alternatives or state when not to use it.

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

• image_editA
  3.8/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explains the purpose and parameters but does not mention side effects, permissions, whether the original file is modified, or how the output is delivered (e.g., saved to output_dir, returned as a URL, etc.). This is a significant gap for a mutation-like 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: a one-sentence purpose followed by a structured Args list. Each parameter entry is necessary and informative, with no redundancy or filler. The format is front-loaded and easy to scan.

  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 the tool's complexity (6 parameters, no annotations), the description covers parameters well, but it omits behavioral details such as default output location, whether output_dir is required to save results, and error handling. The presence of an output schema partially mitigates the lack of return-value documentation, but overall completeness is only adequate.

  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?

  Schema description coverage is 0%, but the description compensates fully by explaining every parameter with specific constraints: absolute paths for image_path, prompt semantics for what to preserve/remove/modify, size must be multiples of 8, and output_dir must be within the safe root. This adds substantial meaning beyond the bare schema.

  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 that the tool uses a local reference image via MetaRouter to edit or perform image-to-image, specifying both the action and resource. This distinguishes it from siblings like image_generate (which likely generates from text) and image_batch_edit (which implies batch processing).

  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 that the tool should be used when a local reference image is available for editing, but it does not explicitly state when to use this tool versus alternatives or provide any exclusion criteria. No alternatives are named, leaving usage guidance mostly implicit.

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

• image_multi_referenceA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It discloses the input limit (2-10) and that images are local, but does not mention output file handling, side effects, or any prerequisites. The prompt guidance implies behavioral expectations of the model, but important operational details are absent.

  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, front-loaded with the core function and followed by a focused prompt guidance tip. No redundant or filler content; every sentence adds value.

  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 the tool has 6 parameters and no annotations, the description is not fully complete. It covers the core behavior and offers prompt guidance, and the presence of an output schema reduces the need to explain return values. However, optional parameters and explicit usage exclusions are missing, leaving moderate gaps for an agent to invoke the tool optimally.

  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 must compensate. It partially explains the prompt parameter (must specify each reference image's contribution) and implies image_paths are local file paths. However, it ignores size, model, quality, and output_dir entirely, leaving these parameters undocumented and under-specified.

  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 verb+resource: 'fuses 2 to 10 local reference images to generate a new image.' This explicitly differentiates it from sibling tools like image_generate (likely text-to-image) and image_edit (single-image editing), establishing a distinct multi-reference generation purpose.

  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 provides clear context: use when you have 2-10 local reference images to synthesize. It also gives explicit prompt-writing guidance ('describe which composition, color scheme, character, or product features each reference image provides'), which aids correct usage. However, it does not explicitly contrast with alternatives or state when not to use it.

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

• image_generateA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explains defaults (gpt-image-2, quality), constraints (size multiples of 8, n 1-4), and automatic model switching for ultra-large sizes. However, it does not disclose whether the tool saves files, what the return value looks like, or potential side effects, leaving some behavioral transparency gaps.

  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 well-structured, with a one-sentence purpose followed by a bulleted list of argument explanations. Every sentence provides useful information without redundancy or waste.

  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 complexity (6 parameters, 1 required) and lack of annotations, the description covers all parameters, defaults, constraints, and usage recommendations. It also notes output safety. It does not mention explicit error conditions or prerequisites, but the output schema likely covers return values. Overall, it is quite complete for a generation tool.

  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 schema has zero description coverage, so the description fully compensates by documenting all 6 parameters with detailed semantics: prompt (subject, composition, style, lighting, prohibited content), size (format and multiple-of-8 constraint), model (default and auto-upgrade), n (range and recommendation), quality (default), and output_dir (safety constraint). This is significantly more informative than the schema alone.

  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 '通过 MetaRouter 文生图' (generate images from text via MetaRouter), which is a specific verb+resource. It distinguishes from sibling tools like image_edit, image_batch_edit, and image_multi_reference by focusing on generation rather than editing or reference-based tasks.

  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 for when to use this tool: it is for text-to-image generation. It includes usage tips such as '高分辨率建议使用 1' and '超大尺寸自动使用 gpt-image-2-pro', which help with parameter choices. However, it does not explicitly mention alternatives or exclusions, such as when to use image_edit instead.

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

• server_infoA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It adds an important safety-related trait: it does not return the full API key, which is a key transparency point. However, it does not explicitly state whether the operation is read-only or mention other behavioral traits like 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 a single, front-loaded sentence that is concise and to the point. It conveys the core purpose and a key safety exclusion without any redundant content.

  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 zero-parameter tool with an output schema present, the description addresses the primary need (what is returned and what is not) and is complete for its simple scope. The presence of an output schema covers detailed return fields, so further description is unnecessary.

  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 input schema fully covers them. The description adds no parameter specifics, which is unnecessary here. The baseline of 4 for no parameters 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 tool's function: it returns the current MetaRouter MCP security runtime configuration, and explicitly notes what it does not return (full API key). This distinguishes it from the image-related sibling tools and provides a specific verb-resource pair.

  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?

  There is no explicit statement about when to use this tool or when to avoid it. The sibling tools are all image-generation/edit tools, which implies server_info is for server-level queries, but the description does not say 'use when you need server configuration' or provide any exclusions.

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