Server Quality Checklist

Tool Scores

• nanobanana_generate_imageA
  3.9/5.0
  Behavior4/5

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

  Annotations already indicate read-only and non-destructive behavior, but the description adds valuable context beyond annotations: it explains error handling (API key requirements, rate limits, content policy), provides best practices for prompts, and notes model-specific features (e.g., resolution for Pro only). No contradiction with annotations.

  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 well-structured with clear sections (overview, args, returns, examples, error handling) and front-loaded key information. It is appropriately sized but could be slightly more concise by integrating some schema details (e.g., parameter defaults) that are redundant.

  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, no output schema), the description is mostly complete: it covers purpose, parameters, returns, examples, and error handling. However, it lacks explicit guidance on when to use versus sibling tools, and some behavioral details (e.g., response time, cost implications) are not addressed, leaving minor gaps.

  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 extra semantics (e.g., 'For best results, be descriptive' for prompt, model options with quality/fast trade-offs), but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate given high schema 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: 'Generate high-quality images from text descriptions using Google's Nano Banana models.' It specifies the verb ('generate'), resource ('images'), and distinguishes from siblings by focusing on generation rather than composition, editing, or listing models.

  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 provides implied usage through examples and best practices (e.g., 'be descriptive about subject, style, lighting'), but does not explicitly state when to use this tool versus alternatives like nanobanana_edit_image or nanobanana_compose_images. No exclusions or prerequisites are mentioned beyond error handling notes.

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

• nanobanana_compose_imagesA
  4.1/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds valuable behavioral context beyond annotations by specifying image limits (up to 14 total, with breakdowns for objects and humans), which helps the agent understand constraints. It doesn't mention rate limits, authentication needs, or processing time, but adds meaningful operational context.

  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 well-structured with clear sections (purpose, use cases, limits, args, returns, examples) and front-loaded key information. It's appropriately sized for a complex tool, though the 'Args' and 'Returns' sections could be more concise since they largely repeat schema information.

  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, image processing), the description provides good context with use cases, limits, and examples. While there's no output schema, the 'Returns' section adequately documents the response structure. The description could benefit from more guidance on prompt engineering or error handling, but covers most essential aspects.

  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 by briefly mentioning the 'images' array structure and model requirement, but doesn't provide additional semantic context or usage examples for parameters beyond what's in the schema 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 tool's purpose with specific verbs ('compose new images', 'transfer styles', 'maintain character consistency', 'combine objects') and resources ('multiple reference images', 'Nano Banana Pro'). It distinguishes from sibling tools by focusing on multi-image composition rather than editing single images, generating from scratch, or listing models.

  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 for when to use this tool through the bullet points of use cases (group compositions, style transfer, character consistency, object combination) and the limits section specifying image type constraints. However, it doesn't explicitly state 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.

• nanobanana_edit_imageA
  4.2/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond what annotations provide. While annotations indicate read-only and non-destructive operations, the description elaborates on what the model actually does (add/remove/modify elements, change style/lighting/colors, adjust composition, apply filters), maintains original style/context, and includes error handling details. This provides practical behavioral insight that annotations alone don't convey.

  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 well-structured with clear sections (purpose, capabilities, args, returns, examples, error handling) and front-loads the core functionality. While comprehensive, some sections like the detailed parameter documentation could be more concise given the schema already covers them thoroughly. Most sentences earn their place by adding value.

  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 (image editing with AI models), the description provides excellent contextual completeness. It covers purpose, capabilities, parameters, return values, examples, and error handling. While there's no output schema, the 'Returns' section thoroughly documents the response structure. The combination of rich description and comprehensive annotations makes this highly complete.

  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?

  With 100% schema description coverage, the schema already thoroughly documents all parameters. The description's 'Args' section essentially repeats what's in the schema without adding significant additional semantic context. The baseline score of 3 is appropriate since the schema does the heavy lifting, though the description provides some clarification about default values and model capabilities.

  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 verb ('Edit') and resource ('an existing image'), and distinguishes it from siblings by specifying it's for editing existing images (vs. generating new ones with nanobanana_generate_image or composing multiple images with nanobanana_compose_images). The opening sentence establishes this distinction immediately.

  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 for when to use this tool ('Edit an existing image using text prompts') and includes examples that illustrate appropriate use cases. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the sibling tools, which prevents a perfect score.

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

• nanobanana_list_modelsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, covering safety and idempotency. The description adds useful context about the return structure (array of model information objects with specific fields) and output format options, which goes beyond annotations. No contradiction with annotations.

  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 well-structured and front-loaded with the core purpose, followed by bullet points detailing return information and a concise parameter/return section. 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 optional parameter, read-only operation) and rich annotations, the description is mostly complete. It details return values since there is no output schema, but could slightly improve by mentioning if the list is paginated or static. Overall, it provides sufficient context for effective use.

  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%, with the parameter 'response_format' fully documented in the schema (including enum values and default). The description repeats some of this information but adds minimal extra meaning, such as noting 'markdown' for human-readable and 'json' for machine-readable, which is already implied in the schema. Baseline 3 is appropriate as the schema does the heavy lifting.

  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 verb ('List') and resource ('available Nano Banana image generation models and their capabilities'), distinguishing it from sibling tools that compose, edit, or generate images. It explicitly identifies what information is returned, making the purpose unambiguous.

  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 by listing models for reference before using generation tools, but does not explicitly state when to use it versus alternatives or any exclusions. It provides clear context as a reference tool, but lacks explicit guidance on when not to use it.

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