Server Quality Checklist

Tool Scores

• describe_imageC
  2.9/5.0
  Behavior2/5

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

  No annotations provided, so description must carry behavioral disclosure. It does not mention authorization needs, rate limits, error handling, or output format. Only states basic function.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Description is concise and front-loaded with essential information (model restriction and function). However, could be better structured with clearer sections.

  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?

  Tool has 7 parameters with nested objects and no output schema. Description fails to explain return values, error behavior, or usage examples. Insufficient for a complex 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 covers 71% of parameters with descriptions. Description adds limited value beyond schema (e.g., listing input methods). Baseline score due to high schema coverage.

  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?

  Description clearly states it describes an image for a text-only agent and lists input types (path, base64, URL). Distinguishes from sibling tools like 'compare_images' and 'ocr_image' implicitly by focusing on description, but could be more explicit.

  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 on when to use this tool vs alternatives like 'answer_about_image'. Includes a model restriction (GLM/DeepSeek) but does not explain usage context or edge cases.

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

• ocr_imageB
  3.1/5.0
  Behavior2/5

  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 does not disclose read-only nature, error handling (e.g., no text found), or return format. The model restriction is mentioned but other behavioral traits like resource consumption or side effects are omitted.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is brief (two sentences) and front-loaded with the purpose. The Chinese note is important but adds some clutter; an English-only agent might need parsing. Still, the structure is efficient with no wasted words.

  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?

  No output schema is provided, and the description does not explain what the tool returns (e.g., extracted text, structure). With 7 parameters, details like maxTokens behavior, detail levels, and model override are not mentioned, leaving significant gaps for an agent to use the tool 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?

  Schema coverage is 71% (5 of 7 parameters have descriptions). The description adds context for 'language' and 'preserveLayout' as optional hints, but most parameter semantics are already in the schema. The _caller_model parameter's schema description already includes the restriction; description does not add beyond that.

  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 clearly states the tool extracts visible text from an image, which matches the name 'ocr_image'. It mentions optional language and layout hints, distinguishing it from sibling tools that answer questions, compare, or describe images. However, it does not explicitly differentiate from 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 includes a model restriction note ('仅限 GLM/DeepSeek 系列模型调用'), which is a usage guideline. But it lacks explicit when-to-use or when-not-to-use guidance compared to sibling tools (e.g., use for text extraction, not for image interpretation).

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

• answer_about_imageA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the disclosure burden. It reveals the model restriction (GLM/DeepSeek only) and implies a text output. However, it does not detail error handling, return format, or other behavioral traits like rate limits or auth requirements.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is efficient with one core sentence and a necessary prefix. It is front-loaded and contains no wasted words. The Chinese prefix could be confusing for non-Chinese agents but is essential for the restriction.

  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 the tool's complexity (6 parameters, nested object schema, no output schema, no annotations), the description is too brief. It lacks details on output format, error cases, and process expectations. The sibling tools are not cross-referenced.

  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?

  The schema coverage is 67% (medium) and the description adds no extra meaning to parameters. It does not explain parameter usage or constraints beyond what is in the schema. For a tool with multiple parameters including nested objects, this is insufficient.

  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: answering a specific question using visual evidence from one image. It uses a specific verb and resource, and distinguishes itself from sibling tools like compare_images (two images), describe_image (general description), and ocr_image (text extraction).

  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 implies when to use this tool (for answering specific questions about a single image) vs. siblings. The Chinese prefix explicitly restricts usage to GLM/DeepSeek models. However, it does not explicitly state when not to use it or provide alternatives.

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

• compare_imagesA
  3.6/5.0
  Behavior2/5

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

  No annotations are provided, and the description only states that it 'summarizes differences' without disclosing behavioral traits like error handling, authentication needs, or effect on system. This is insufficient for a tool with no annotation safety net.

  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?

  Description is a single sentence plus a bracketed restriction, with no wasted words. It is front-loaded with the action and model restriction.

  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 complexity (nested objects, multiple image input methods, no output schema), the description is minimal. It does not explain image input options or output format, but the schema covers input details. Adequate but with gaps for an agent to fully understand without schema inspection.

  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 57%, but the description text adds no additional meaning to parameters beyond what the schema provides. It does not mention image input options or any parameter details, leaving a gap in understanding for complex nested inputs.

  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?

  Description clearly states 'Compare two images and summarize relevant differences' with a specific verb and resource. It distinguishes from sibling tools (single-image tasks) by explicitly mentioning comparison and two 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?

  Description includes a model restriction ('仅限 GLM/DeepSeek 系列模型调用') which guides when to use, and the context of 'for a text-only agent' implies suitable scenarios. However, it does not explicitly exclude alternatives or mention prerequisites.

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