Server Quality Checklist

Tool Scores

• analyze_fileA
  4/5.0
  Behavior2/5

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

  Annotations are absent, so the description carries the full burden. It mentions the model used and parameter roles, but does not disclose behavioral traits such as whether the file is uploaded to an external service, file size/type limitations, or that this is a read-only operation. This is a significant gap for a tool handling user files.

  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 with the tool's purpose, followed by a clean, bulleted argument list. Every sentence earns its place without unnecessary 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?

  With an output schema present, return values are covered elsewhere. The description provides adequate input semantics and usage context. However, it lacks constraints like accepted file extensions beyond 'etc.' and privacy/security notes, which would make it more complete for an agent.

  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 0% description coverage, but the description compensates by documenting all 5 parameters with meaningful explanations (e.g., file supports URL/data URI/local path, temperature range 0-1, thinking toggles deep thinking mode). This adds value 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 analyzes documents/files using GLM-4.6V-Flash, listing supported formats (PDF, TXT, etc.) and access methods (URL, data URI, local path). This distinguishes it from siblings analyze_image and analyze_video, which target different media types.

  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 context: this tool is for analyzing document-like files, and the sibling names imply image/video alternatives. However, it does not explicitly state when NOT to use it or directly mention alternative tools, so it stops short of full guidance.

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

• analyze_imageA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It discloses the model (GLM-4.6V-Flash) and the types of analysis supported, but does not address privacy implications, return format specifics, or failure modes. This is adequate but not comprehensive.

  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 with an opening sentence that states the purpose followed by a structured list of parameter descriptions. No redundant text or unnecessary details.

  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?

  An output schema exists, so return values are presumably documented. The description covers parameters and general purpose well. It lacks explicit alternative guidance and edge-case limitations, but for a straightforward image analysis tool it is sufficiently complete.

  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 0% description coverage, so the description's Args section is essential. It clearly explains all five parameters, including supported URL formats for image, the purpose of prompt, and ranges (temperature 0~1, max_tokens). This fully compensates for 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 states '使用 GLM-4.6V-Flash 分析一张图片' (use GLM-4.6V-Flash to analyze an image) and lists specific capabilities such as OCR, content understanding, table parsing, and defect detection. This clearly distinguishes it from sibling tools analyze_video and analyze_file.

  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 usage for image analysis but does not explicitly mention when to prefer this tool over siblings or provide exclusions. No guidance on alternatives is given, so the usage context is inferred rather than explicit.

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

• analyze_videoA
  4.3/5.0
  Behavior3/5

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

  No annotations are present, so the description must disclose behavior. It mentions the underlying model (GLM-4.6V-Flash) and input constraints (URL/local file), but does not describe potential side effects, rate limits, failure modes, or output format. This is adequate but not rich.

  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, with a one-sentence intro followed by a clean list of five parameters. No wasted words.

  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 (5 parameters, one required) and no annotations, the description covers all arguments and the core purpose. It doesn't mention video length/size limits or return values, but an output schema exists, so that gap is partially mitigated. Overall it's a solid 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 description provides a full 'Args' section that explains each parameter beyond the schema: video supports URL, data URI, or local file; prompt is the question/instruction; thinking is a deep-thinking toggle; temperature is sampling temperature (0-1); max_tokens is the maximum output. This fully compensates for the schema's 0% description 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 clearly states the tool's purpose: using GLM-4.6V-Flash to analyze a video, with the input requirement of a URL or local file. It explicitly identifies the media type (video), distinguishing it from sibling tools for images and files.

  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 context on when to use this tool: whenever video analysis is needed, with supported input formats listed. However, it does not explicitly mention alternatives or when not to use it, though sibling tool names imply that image and file analysis are separate.

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