Server Quality Checklist

Tool Scores

• edit_imageC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the AI model used and editing capabilities but omits critical information like rate limits, authentication requirements, whether edits are destructive to original images, processing time, or error handling. For a complex image editing tool, this leaves significant behavioral gaps.

  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 appropriately concise with two sentences that efficiently communicate the core functionality. The first sentence establishes the main purpose, and the second lists key capabilities. No wasted words, though it could be slightly more structured by separating capabilities more clearly.

  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?

  For a complex image editing tool with 5 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns (edited images, success/failure indicators, error formats), doesn't mention prerequisites or limitations, and provides minimal guidance on parameter usage despite the schema doing most of the technical documentation.

  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 description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds minimal value beyond the schema - it mentions 'multi-image mixing' which relates to the 'images' array parameter, but doesn't provide additional semantic context about how parameters interact or practical usage examples.

  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: 'Edit one or more images using Google Gemini 3.0 (Nano Banana Pro).' It specifies the verb ('Edit'), resource ('images'), and technology used, but doesn't explicitly differentiate from sibling tools like 'describe_image' or 'generate_image' beyond mentioning editing capabilities.

  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 its siblings ('describe_image' and 'generate_image'). It mentions capabilities like 'style transfer, object manipulation, and multi-image mixing' but doesn't clarify whether these are exclusive to this tool or available in alternatives.

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

• generate_imageC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions some constraints (e.g., 'up to 4K resolution,' 'up to 14 reference images') but lacks critical details like rate limits, authentication requirements, cost implications, error handling, or output format. For a generative AI tool with potential side effects, this is insufficient.

  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 a single, efficient sentence that front-loads the core purpose and key features. It avoids redundancy and wastes no words, though it could be slightly more structured (e.g., separating purpose from constraints).

  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 (generative AI with multiple parameters) and lack of annotations or output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., image data, file path), error conditions, or usage limits, leaving significant gaps for an agent to operate effectively.

  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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema—it mentions 'up to 4K resolution' and 'up to 14 reference images,' which are partially covered in the schema's descriptions. Baseline 3 is appropriate as the schema does most of the work.

  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: 'Generate an image using Google Gemini 3.0 (Nano Banana Pro).' It specifies the verb ('Generate') and resource ('image'), and mentions key capabilities like resolution and reference images. However, it doesn't explicitly differentiate from sibling tools like 'describe_image' or 'edit_image' beyond the core generation function.

  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 its siblings ('describe_image' and 'edit_image'). It mentions technical capabilities (e.g., up to 4K resolution, reference images) but doesn't indicate scenarios where this tool is preferred over alternatives or any prerequisites for use.

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

• describe_imageB
  3.3/5.0
  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 uses Google Gemini and returns text descriptions, but doesn't cover important aspects like rate limits, authentication needs, error handling, or whether the operation is idempotent. The description adds some context but leaves significant gaps for a tool that interacts with an external AI service.

  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 extremely concise with just one sentence that efficiently communicates the core functionality, technology used, and output format. Every word earns its place with no wasted text, making it easy to parse and understand quickly.

  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?

  For a tool with 3 parameters, 100% schema coverage, but no annotations or output schema, the description provides basic functionality context but lacks important behavioral details. It covers what the tool does and what technology it uses, but doesn't address reliability, limitations, or what the agent should expect in terms of response format or potential errors.

  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 description coverage is 100%, so the schema already documents all three parameters thoroughly. The description mentions analyzing 'one or more images' which aligns with the 'images' array parameter, and references 'custom analysis prompt' which maps to the 'prompt' parameter, but doesn't add meaningful semantic context beyond what the schema provides.

  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 verb 'analyze and describe' and the resource 'one or more images using Google Gemini', with the output format 'text description only'. It distinguishes from sibling tools like 'edit_image' and 'generate_image' by focusing on analysis rather than modification or creation, though it doesn't explicitly name these alternatives.

  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 and description, but doesn't provide explicit guidance on when to use this tool versus alternatives like 'edit_image' or 'generate_image'. It mentions the default prompt behavior but lacks context about specific scenarios or exclusions.

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