Server Quality Checklist

Tool Scores

• ocr_imageA
  3.5/5.0
  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. It discloses the return format (text blocks with confidence scores and bounding boxes), which is useful, but it does not mention potential errors, permissions, side effects, or backend behavior with edge cases.

  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 core purpose ('OCR text from an image'), followed by a brief explanation of the output. Every sentence is informative, with no wasteful repetition.

  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?

  The tool is simple with one parameter, and the description covers the invocation and output format. The presence of an output schema reduces the need to describe return values in detail. However, it lacks usage guidance and constraints like supported image formats or image size limits.

  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 description adds meaningful details for 'image_path' beyond the schema, specifying it must be an absolute path and under the home directory. Since schema coverage is 0%, this description compensates well for the single parameter.

  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 states a specific verb 'OCR' and resource 'image', clearly defining the tool's function. It also mentions the output type (text blocks with confidence scores and bounding boxes), but it does not explicitly distinguish from the sibling 'extract_text', which could overlap in functionality.

  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?

  The description does not provide guidance on when to use this tool versus alternatives like 'extract_text' or 'image_metadata'. It only implies usage for image files but lacks explicit context or exclusions.

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

• extract_textA
  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 burden of behavioral disclosure. It usefully reveals that the tool returns a 'single JSON response' and imposes a security constraint ('must be under home directory'). However, it does not mention error handling, supported file types, or explicitly state that it is a read-only operation, leaving some behavioral aspects undisclosed.

  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 and front-loaded with the primary purpose. It uses three concise sentences with no unnecessary fluff, and the Args section clearly explains the parameter without redundancy.

  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 one-parameter tool with an output schema, the description covers the essential invocation details: what it does, the path requirement, and the combined output. It does not specify image format limitations or failure modes, but these are not critical for a basic extraction tool. Overall, it is adequately 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 input schema provides no description for the single parameter (coverage 0%), so the description fully compensates by explaining that image_path must be an absolute path under the home directory. This adds crucial semantic meaning beyond the schema's bare string type.

  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 'Extract all text and metadata from an image' with a specific verb and resource. It also distinguishes itself from siblings by calling itself a 'convenience wrapper' that combines OCR text extraction with image metadata, making it distinct from the standalone ocr_image and image_metadata 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 implies usage context by labeling the tool a 'convenience wrapper' that combines OCR and metadata into one response, suggesting it should be used when both are needed. However, it does not explicitly state when not to use it or directly reference the sibling alternatives, 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.

• image_metadataA
  4.4/5.0
  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 for behavioral disclosure. It clearly indicates a read-only operation via 'extract' and details what the tool returns, plus the path constraint that the file must be under home directory. However, it does not mention error handling, file type limitations, or 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?

  The description is concise, opening with a direct purpose statement followed by a focused list of return categories. The explicit Args section adds necessary detail without redundancy, and every sentence contributes to understanding.

  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 an output schema, the description provides sufficient context: it states the purpose, lists the returned metadata types, and explains the path constraint. Despite lacking explicit usage guidance, the core operation is fully specified for the agent to invoke correctly.

  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 provides only a type-less 'path' property with no description. The description compensates fully by defining 'path' as 'Absolute path to the image file' and adding the additional constraint that it must be under the home directory, giving the agent complete parameter semantics.

  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 'Extract full metadata from an image,' which clearly states the verb and resource. It then enumerates specific metadata categories (file info, image properties, EXIF), distinguishing it from sibling tools like ocr_image and extract_text that handle 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 Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not explicitly guide when to use this tool versus alternatives. While it is clear the tool is for metadata extraction, it never mentions the text-focused siblings or provides when/when-not guidance, leaving usage to be implied.

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