Server Quality Checklist

Tool Scores

• apply_filterB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool applies filters and saves output, but doesn't mention whether the original file is modified, what permissions are needed, error conditions, or performance characteristics. The default output path behavior is helpful but insufficient for a mutation tool with zero annotation coverage.

  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 efficiently structured with a clear purpose statement, bulleted filter list, and parameter explanations. Every sentence adds value: the first states the core function, the second enumerates options, and the third explains parameters with useful defaults. No wasted words.

  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 an output schema (which presumably describes the return value), the description doesn't need to explain return values. However, for a mutation tool with 3 parameters and no annotations, it should provide more behavioral context about side effects, error handling, and constraints. The parameter explanations are good but the overall context is incomplete.

  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?

  With 0% schema description coverage, the description compensates well by explaining all three parameters: 'path' as absolute file path, 'filter_name' with enumerated options, and 'output_path' with default behavior. It adds meaningful context beyond the bare schema, though it doesn't specify file format constraints or filter-specific details.

  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's purpose: 'Apply a filter to an image' with a specific verb ('apply') and resource ('image'). It distinguishes from siblings by focusing on filtering rather than compression, conversion, cropping, etc. However, it doesn't explicitly differentiate from all siblings (e.g., 'emboss' might overlap with 'edge_enhance' conceptually).

  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 provides no guidance on when to use this tool versus alternatives like 'convert_image' or 'create_thumbnail'. It lists available filters but doesn't explain which filters are appropriate for what scenarios or when to choose this over other image manipulation tools. No exclusions or prerequisites are mentioned.

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

• extract_framesB
  3.4/5.0
  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 of behavioral disclosure. It states the action ('extract frames') and default behaviors (e.g., output directory defaults), but lacks critical details: whether it overwrites existing files, requires specific permissions, handles errors (e.g., invalid paths), has rate limits, or what the output schema returns. For a tool with 5 parameters and no annotations, this is a significant gap in transparency.

  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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by a structured 'Args:' section listing parameters with concise explanations. Every sentence earns its place by providing essential information without redundancy. The formatting enhances readability, making it 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 (5 parameters, no annotations, but has output schema), the description is partially complete. It excels in parameter semantics but lacks behavioral context (e.g., error handling, side effects). The output schema exists, so the description needn't explain return values, but it should cover more operational aspects. For a video processing tool, this leaves gaps in understanding how it behaves in practice.

  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%, so the description must fully compensate. It successfully adds meaning beyond the schema by explaining all 5 parameters: 'path' (absolute path to video), 'interval_seconds' (time between frames), 'max_frames' (maximum to extract), 'output_dir' (directory to save, with default), and 'format' (image format with options). This provides clear semantics, defaults, and constraints not in the schema.

  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's purpose: 'Extract frames from a video at regular intervals.' This specifies the verb ('extract'), resource ('frames from a video'), and method ('at regular intervals'). It distinguishes from siblings like 'convert_video' or 'get_video_info' by focusing on frame extraction rather than format conversion or metadata retrieval. However, it doesn't explicitly contrast with all siblings (e.g., 'create_thumbnail' might also extract frames).

  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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., video file accessibility), compare to siblings like 'create_thumbnail' for single-frame extraction, or specify use cases (e.g., for analysis vs. preview). The only implied context is video frame extraction, but no explicit when/when-not rules are given.

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

• crop_imageA
  3.6/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool crops an image and saves it, implying mutation, but doesn't mention permissions, whether the original file is modified, error handling, or format support. The coordinate explanation is helpful but insufficient for a mutation 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 efficiently structured: a clear purpose statement, a key behavioral note (coordinate system), and a parameter list with brief explanations. Every sentence earns its place, and information is front-loaded with the core functionality first.

  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 6 parameters with 0% schema coverage and no annotations, the description does well on parameters but lacks behavioral context for a mutation tool. The presence of an output schema means return values needn't be explained, but gaps remain in usage guidelines and transparency.

  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%, so the description must compensate fully. It provides clear semantics for all 6 parameters: path specifies the input file, left/top/right/bottom define the crop region in pixels from top-left, and output_path specifies where to save with a default. This adds essential 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 with a specific verb ('crop') and resource ('image'), and distinguishes it from siblings like resize_image, rotate_image, or flip_image by specifying it crops to a specific region. The first sentence directly answers what the tool does.

  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 provides no guidance on when to use this tool versus alternatives like resize_image or create_thumbnail. It mentions coordinate details but doesn't explain use cases or prerequisites, leaving the agent to infer usage from the purpose alone.

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

• flip_imageA
  3.6/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the transformation action and output behavior (saving to a file), but doesn't address important behavioral aspects like whether the operation is destructive to the original file, what permissions are required, error conditions, or performance characteristics. The description provides basic operational context but lacks comprehensive behavioral transparency.

  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 efficiently structured with a clear purpose statement followed by parameter explanations. Every sentence earns its place by providing essential information without redundancy. The formatting with 'Args:' section organizes parameter information effectively while maintaining brevity.

  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 moderate complexity (image transformation with 3 parameters), no annotations, but with an output schema present, the description provides adequate context. It explains the core operation and all parameters, though it could benefit from more behavioral context about file handling, error conditions, or performance. The existence of an output schema means the description doesn't need to explain return values, which helps its completeness.

  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?

  With 0% schema description coverage, the description compensates well by explaining all three parameters: 'path' as the absolute path to the image file, 'direction' with its allowed values ('horizontal' or 'vertical'), and 'output_path' with its default behavior. The description adds meaningful semantics beyond what the bare schema provides, though it doesn't specify file format constraints or path validation rules.

  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 verb ('flip/mirror') and resource ('an image'), specifying the transformation type (horizontal or vertical). It distinguishes from siblings like rotate_image, resize_image, and crop_image by focusing specifically on mirroring operations rather than other image manipulations.

  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 provides no guidance on when to use this tool versus alternatives. While it's clear this is for flipping images, there's no mention of when flipping is appropriate versus rotating, cropping, or applying filters. No prerequisites, exclusions, or comparison to sibling tools are provided.

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

• rotate_imageA
  3.6/5.0
  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 mentions that the tool saves an output file, implying a write operation, but doesn't disclose behavioral traits like whether it modifies the original file, handles errors, supports specific image formats, or has performance considerations. The description is minimal beyond basic functionality.

  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 front-loaded with the core purpose in the first sentence, followed by a structured Args section that efficiently documents parameters without redundancy. Every sentence earns its place, making it appropriately sized and easy to scan.

  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 moderate complexity (4 parameters, no annotations, but with an output schema), the description is reasonably complete. It covers the purpose and parameters well, and since an output schema exists, it needn't explain return values. However, it could improve by adding more behavioral context or usage guidelines to fully compensate for the lack of annotations.

  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?

  With 0% schema description coverage, the description compensates by explaining all 4 parameters in the Args section: 'path' as the absolute file path, 'degrees' as the rotation angle counter-clockwise, 'expand' to fit the rotated image, and 'output_path' with a default. This adds meaningful semantics beyond the bare schema, though it could elaborate on constraints like valid degree ranges.

  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 with a specific verb ('rotate') and resource ('image'), and distinguishes it from siblings like 'flip_image' or 'resize_image' by specifying rotation by degrees. The first sentence directly answers what the tool does.

  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 provides no guidance on when to use this tool versus alternatives like 'flip_image' or 'crop_image'. It lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage from the purpose alone.

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

• get_image_infoA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates this is a read-only operation ('Get') and specifies what information is returned, but lacks details on error handling, permissions needed for file access, performance characteristics, or whether it modifies the file. This is adequate but has gaps for a tool with no annotation coverage.

  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 front-loaded with the core purpose, followed by specific return details and parameter explanation in a clear, bullet-like structure. Every sentence adds value without redundancy, making it efficient and easy to parse.

  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 low complexity (one parameter), no annotations, and the presence of an output schema (which handles return values), the description is reasonably complete. It covers purpose, returns, and parameter semantics, though it could benefit from more behavioral context like error cases or file access requirements to be fully comprehensive.

  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 context for the single parameter 'path' by specifying it as an 'Absolute path to the image file,' which clarifies the expected input format beyond the schema's basic string type. With 0% schema description coverage and only one parameter, this compensates well, though it doesn't detail path validation or supported file formats.

  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's purpose with a specific verb ('Get') and resource ('detailed information about an image file'), distinguishing it from siblings like 'get_video_info' which handles video files. However, it doesn't explicitly differentiate from other read-only siblings like 'create_thumbnail' or 'extract_frames' that also retrieve image data.

  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 by specifying it returns image metadata, suggesting it should be used when such information is needed. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_video_info' for videos or 'strip_metadata' for removing metadata, nor does it mention prerequisites or exclusions.

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

• convert_videoA
  3.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but lacks critical behavioral details. It doesn't disclose whether this is a destructive operation (overwrites files?), what permissions are needed, potential side effects, or error handling. The mention of default values and supported formats adds some context but falls short of comprehensive behavioral transparency.

  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 efficiently structured with a clear purpose statement followed by a bullet-point-like parameter explanation. Every sentence earns its place by providing essential information without redundancy. The formatting with 'Args:' section enhances readability while maintaining brevity.

  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 (video conversion with multiple parameters), no annotations, but with output schema present, the description is reasonably complete. It thoroughly documents parameters and conversion options but could better address behavioral aspects like file safety, performance characteristics, or common use cases relative to sibling tools.

  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?

  With 0% schema description coverage, the description fully compensates by explaining all 5 parameters in detail. It clarifies 'path' as absolute path, 'format' with examples and supported list, 'output_path' default behavior, 'resolution' format examples, and 'crf' meaning and range. This adds substantial value 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 with specific verbs ('convert') and resources ('video'), distinguishing it from siblings like 'convert_image' or 'extract_frames'. It explicitly mentions both format and resolution conversion, making the scope unambiguous.

  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 through the stated purpose but provides no explicit guidance on when to use this tool versus alternatives like 'extract_frames' or 'create_thumbnail'. It doesn't mention prerequisites, error conditions, or comparative scenarios with sibling tools.

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

• convert_imageA
  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 full burden. It discloses that the tool writes a new file (implied by 'save'), supports specific formats, and has default behaviors for output_path and quality. However, it lacks details on error handling, permissions, or side effects like overwriting 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 front-loaded with the core purpose, followed by a concise list of supported formats and well-structured parameter explanations. Every sentence adds value without redundancy, making it efficient and easy to parse.

  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 moderate complexity, no annotations, and an output schema (which handles return values), the description is largely complete. It covers purpose, parameters, and supported formats, but could improve by mentioning input format support or error cases for a higher score.

  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?

  Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics for all parameters: path as an absolute file path, format as target with examples, output_path with default behavior, and quality with range and default. This goes beyond the bare schema, though it could specify format case-sensitivity or quality applicability.

  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 with a specific verb ('convert') and resource ('image'), distinguishing it from siblings like compress_image, resize_image, or convert_video. It specifies the transformation from one format to another, making the scope unambiguous.

  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 format conversion but does not explicitly state when to use this tool versus alternatives like compress_image or create_thumbnail. It lists supported formats, which provides some context, but lacks guidance on exclusions or prerequisites for use.

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

• create_thumbnailA
  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 full burden. It explains the core behavior (resizing to fit square, preserving aspect ratio) and mentions default behavior for output_path, but doesn't cover error handling, file format support, permissions needed, or what happens if output_path exists. Some behavioral context is provided 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 efficiently structured with a clear purpose statement followed by parameter explanations. Every sentence adds value with no redundant information. The Args section is well-organized and directly supports tool invocation.

  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 has an output schema (which handles return values), no annotations, and good parameter coverage in the description, the description is reasonably complete. It explains the transformation behavior and parameters adequately, though could benefit from more behavioral context about edge cases or limitations.

  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?

  With 0% schema description coverage, the description compensates well by explaining all three parameters: path (absolute path to image), size (thumbnail size in pixels with default 256), and output_path (where to save with default naming convention). It adds meaningful context beyond the bare schema types.

  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 creates a square thumbnail from an image, specifying it resizes to fit within a square while preserving aspect ratio. This distinguishes it from sibling tools like resize_image (general resizing) and crop_image (cropping rather than fitting).

  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 creating thumbnails with square aspect ratios, but doesn't explicitly state when to use this versus alternatives like resize_image or crop_image for similar tasks. No guidance on prerequisites or exclusions is provided.

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

• compress_imageA
  4.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It adequately describes the core behavior (compression with optional resizing) and format handling, but lacks details about permissions needed, whether the operation is destructive to the original file, error conditions, or performance characteristics. The description doesn't contradict any annotations since none exist.

  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 efficiently structured with a clear purpose statement followed by a well-organized parameter section. Every sentence earns its place by providing essential information without redundancy. The formatting with bullet-like parameter explanations enhances readability while maintaining brevity.

  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 moderate complexity (5 parameters, mutation operation), no annotations, but with an output schema present, the description is mostly complete. It covers the core functionality and parameters well, and the output schema presumably handles return values. However, for a mutation tool with no annotations, it could benefit from more behavioral context about side effects or error handling.

  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?

  With 0% schema description coverage, the description fully compensates by providing clear semantics for all 5 parameters. Each parameter is explained with its purpose, constraints (e.g., '1-100' for quality), default values, and behavioral effects (e.g., 'Image will be downscaled if wider'). This adds significant value 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 with a specific verb ('compress') and resource ('image'), and distinguishes it from siblings by focusing on file size reduction rather than format conversion (convert_image), resizing (resize_image), or metadata removal (strip_metadata). The first sentence directly answers 'what does this tool do?'

  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 about when to use this tool ('Works best with JPEG and WebP. PNG files will be converted to optimized PNG'), which helps differentiate it from format-focused siblings like convert_image. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the siblings, such as when resize_image might be more appropriate for pure resizing without compression.

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

• strip_metadataA
  4.3/5.0
  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 of behavioral disclosure. It effectively describes the tool's behavior: it removes metadata for privacy, creates a clean copy (implying non-destructive operation), and specifies default output naming. However, it does not mention potential side effects, file format support, or error conditions, leaving some 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 front-loaded with the core purpose, followed by outcome and parameter details in a structured format. Every sentence adds value without redundancy, and the Args section is efficiently formatted, making it easy to parse quickly.

  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 moderate complexity (2 parameters, no annotations, but with an output schema), the description is largely complete. It covers purpose, behavior, and parameters well. The presence of an output schema means return values need not be explained, but it could benefit from mentioning supported image formats or error handling for full completeness.

  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%, so the description must compensate fully. It clearly explains both parameters: 'path' as the absolute path to the image file, and 'output_path' with its default behavior ('Defaults to <name>_clean.<ext>'). This adds essential meaning beyond the bare schema, making parameter usage clear.

  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 specific action ('Remove all EXIF and metadata') and target resource ('from an image'), distinguishing it from sibling tools like compress_image or resize_image. It explains the privacy purpose and outcome ('Creates a clean copy of the image with no embedded metadata'), making the tool's function unambiguous.

  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 privacy purposes when metadata removal is needed, but does not explicitly state when to use this tool versus alternatives (e.g., get_image_info for viewing metadata) or any prerequisites. It provides basic context but lacks explicit guidance on tool selection among siblings.

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

• get_video_infoA
  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. It discloses key behavioral traits: it returns specific metadata (duration, resolution, etc.), requires external dependency (ffprobe), and implies a read-only operation (no destructive hints). However, it doesn't mention error handling, performance characteristics, or rate limits.

  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 appropriately sized and front-loaded: the first sentence states the purpose, followed by return details, prerequisites, and parameter explanation. Every sentence adds value with zero waste.

  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 moderate complexity (single parameter, read-only operation), no annotations, and the presence of an output schema (which handles return values), the description is complete enough. It covers purpose, prerequisites, parameter semantics, and return information, leaving no critical gaps.

  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 adds significant meaning beyond the input schema, which has 0% coverage. It explicitly defines the 'path' parameter as 'Absolute path to the video file,' clarifying the expected format and usage, which compensates fully for the schema's lack of descriptions.

  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 specific action ('Get detailed information about a video file') and distinguishes it from siblings by specifying it's for video files (not images) and returns metadata rather than performing transformations like convert_video or extract_frames.

  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 through the requirement of ffprobe installation, suggesting this tool should be used when ffprobe is available. However, it doesn't explicitly state when to use this versus alternatives like get_image_info for images or when not to use it (e.g., for non-video files).

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

• resize_imageA
  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 full burden and does well by explaining key behaviors: aspect ratio preservation by default, automatic dimension calculation when only one dimension is provided, and default output naming convention. It doesn't cover error conditions or performance characteristics.

  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 efficiently structured with a clear purpose statement followed by detailed parameter explanations in a labeled 'Args' section. Every sentence adds value with no redundancy or unnecessary information.

  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 complexity (6 parameters, 0% schema coverage, no annotations) and the presence of an output schema, the description provides complete context: clear purpose, parameter semantics, behavioral details, and usage guidance without needing to explain return values.

  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?

  With 0% schema description coverage, the description fully compensates by explaining all 6 parameters in detail: what each parameter does, how they interact (width/height vs. scale), default behaviors, and the output_path default naming convention.

  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 with specific verbs ('resize an image') and resources ('image'), and distinguishes it from siblings by focusing on dimension/scale-based resizing rather than cropping, rotating, or other image operations.

  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 about when to use this tool (resizing by dimensions or scale) and how parameters interact, but doesn't explicitly mention when not to use it or name specific alternatives among the sibling tools.

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