Server Quality Checklist

Tool Scores

• analyze_imagesA
  4.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It explains input constraints (size, count) and return type (joint analysis text), but does not explicitly mention side effects, safety, or error behavior. This is moderate transparency for an analysis tool that likely has none.

  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 with an intro sentence, Args section, and Returns section. Every line adds value, including practical example questions, without wasted words.

  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?

  Given the tool's simple two-parameter interface and the presence of an output schema, the description is complete. It covers purpose, parameter semantics, return type, and usage constraints. No critical information about the tool's operation is missing.

  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%, and the description fully compensates by explaining both parameters in detail. It describes images as a list of paths or URLs with practical size/count limits, and question as a comparison or summary instruction with concrete examples, adding significant meaning beyond the raw 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 the tool performs joint analysis of multiple images with concrete examples (before/after, A/B comparison, multi-frame sequence). This distinguishes it from sibling tools like describe_image which handle single images, making the purpose unambiguous.

  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 through examples and constraints (recommended 2-5 images, each ≤10MB), implying it should be used for comparative or multi-image tasks. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of the top score.

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

• describe_imageA
  4.6/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the burden. It discloses supported image sources (local paths, URLs, file://, data URIs) and states that it returns a text description. It does not mention potential limitations or side effects, but for a simple read-only vision tool, this is mostly sufficient. A note about accuracy or model behavior could push it higher.

  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 well-structured into purpose, usage cases, args, and returns. It is front-loaded with the core purpose, and every sentence adds value. The formatting uses clear paragraph breaks and a simple Args list, making it easy to scan.

  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?

  Given the tool's simplicity (2 parameters, no annotations, output schema present), the description covers all necessary aspects: what it does, when to use it, parameter semantics, and return value. It is complete and self-contained.

  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 description includes an Args section that explains image formats (本地路径, http(s)://, file://, data:image/...;base64,...) and prompt guidance ('越具体越好；留空返回通用描述'), adding significant value beyond the schema, which has zero descriptions for either parameter.

  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 '识别单张图片并返回文字描述' – a specific verb (识别) + resource (单张图片) + output (文字描述). It clearly distinguishes from siblings by emphasizing '单张' and '任意图片' coverage, making it unambiguous when this tool should be selected.

  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 explicitly states when to use: '当用户让你"看/读/识别"一张图片...' and provides an exclusion: '请勿用文件读取工具直接读图片'. However, it does not name sibling alternatives like extract_text_from_image or analyze_images, so the distinction from those tools is implied rather than explicit.

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

• extract_text_from_imageA
  4.6/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden. It discloses that it preserves line breaks/indentation and does not interpret content, which goes beyond the obvious 'extract text' behavior. It does not mention limitations like image quality sensitivity or language support, but for a simple OCR tool the key behavioral aspects are covered.

  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 highly concise: a one-line core definition, a practical use-case sentence, and clearly labeled Args/Returns sections. Every sentence adds value, with no fluff.

  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 tool with a simple text return, the description covers the purpose, input formats, output behavior, and use cases. The presence of an output schema further reduces the need to explain return details. It is self-contained and complete for typical OCR usage.

  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 only gives 'image' as a required string with zero description. The description fully compensates by enumerating accepted formats: local path, http(s) URL, file://, and base64 data URI. This is essential for correct invocation and makes the parameter semantics complete despite 0% schema coverage.

  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 '纯 OCR：逐字提取图片中的全部文字' (pure OCR: extract all text character-by-character), which is a specific verb+resource with clear scope. It also adds '不做解读' (no interpretation), distinguishing it from sibling tools like describe_image or analyze_images.

  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 lists clear use cases (logs, terminal, code, error dialogs, document scans), giving specific context for when to use it. However, it does not explicitly name alternative tools for when interpretation is needed; it only implies this through '不做解读', so it lacks explicit exclusions or alternative tool recommendations.

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

• read_image_infoA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it only validates (read-only) and does not call MiMo API, indicating it's a lightweight, non-invasive operation. It also states the return type (validation result and MIME type), but omits potential error behavior or permissions.

  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 highly concise and well-structured. It begins with a clear one-sentence summary, then provides organized Args and Returns sections. Every part earns its place without redundancy.

  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 simple validation tool with one parameter and an output schema, the description is complete. It explains the purpose, input format, and return concept. Since an output schema exists, detailed return fields are not required in the description.

  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 description coverage is 0%, so the description must compensate. The Args section fully explains the 'image' parameter, enumerating accepted formats: local path, http(s):// URL, file://, or data:...;base64,... This adds complete 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 the tool's purpose: to validate whether an image input can be recognized and return format information, explicitly noting it does not call the MiMo API. This distinguishes it from sibling tools like describe_image and analyze_images, which likely perform deeper analysis.

  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 a clear use case: for troubleshooting image input issues. It implies this is the diagnostic tool to use before attempting more complex operations, but it does not explicitly mention 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.