Server Quality Checklist

Tool Scores

• edit_imageA
  4.2/5.0
  Behavior4/5

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

  The description adds behavior beyond the annotations: "saves the result as a NEW file (never overwrites sources)" and "returns the absolute saved path(s)." These safety and outcome details are valuable context that annotations (readOnlyHint=false, destructiveHint=false) do not provide. 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 three sentences: first states the core purpose and allowed operations, second explains input/output behavior, third states the return value. Every sentence earns its place, with no redundancy or filler. It is front-loaded with the most important 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?

  For a 12-parameter tool with no output schema, the description covers the essential context: what it does, source handling, non-destructive output, and return value. The rich parameter details are already in the schema, so the description is complete without being verbose. Slight gap: it does not mention provider-specific variations, but those are documented in the schema.

  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 fully documents all 12 parameters. The description itself does not elaborate on any parameter semantics, but the baseline 3 is appropriate since the structured data carries the burden and does it well.

  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 a specific verb+resource: "Edit or combine existing image file(s) using a text instruction," and lists concrete operations (modify, restyle, add/remove content, merge references). This clearly distinguishes it from the sibling generate_image tool, which creates new images rather than editing existing ones.

  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 makes it clear the tool is for existing image files ("Reads the source image(s) from disk"), implying the alternative generate_image for new images. However, it does not explicitly state when not to use this tool or name the sibling alternatives, leaving a small gap in explicit guidance.

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

• generate_imageA
  4.5/5.0
  Behavior5/5

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

  The description discloses several behaviors not visible in annotations: real API credit costs, sequential generation slowdown on Gemini for n>1, automatic switch from gpt-image-2 to gpt-image-1.5 for transparent backgrounds, model-specific image size handling, and MCP output token limits for return_image. This goes well beyond the sparse 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 four sentences, each carrying essential info: core function, return value, output_path preference, and cost warning. It is front-loaded with the primary purpose and avoids filler while remaining comprehensive.

  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?

  With no output schema, the description explains the return format (absolute paths + provider/model metadata). It covers cost, output path fallback chain, allowed directories via list_capabilities, transparency caveats, and return_image token limits — a thorough treatment for a 10-param tool with no output schema.

  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?

  All 10 parameters already have detailed descriptions in the JSON schema (100% coverage), so the description adds little per-parameter semantics. The only extra guidance is preferring an absolute output_path and noting cost implications, which doesn't elevate beyond the schema-driven baseline of 3.

  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 a specific verb+resource: 'Generate one or more images from a text prompt using Gemini or OpenAI image models and save them to disk.' This clearly distinguishes it from sibling edit_image (which edits existing images) and names the underlying providers and model families.

  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 explicit usage cues: strongly prefer an absolute output_path, call list_capabilities to see configured providers/allowedDirs, and use low quality for cheap drafts. It doesn't explicitly state when to choose generate_image over edit_image, so it lacks a full when-not-to-use contrast.

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

• list_capabilitiesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by detailing the exact contents of the report (providers, default provider/models, known options, output directory fallback, directory restrictions), which goes beyond the annotations and clarifies expected behavior.

  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, two sentences, with the core purpose front-loaded and a usage hint appended. Every word earns its place, with no fluff or repetition of structured annotations.

  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 simple, no-parameter listing tool, the description fully explains what the tool reports and when to use it. No output schema exists, but the description compensates by listing the kinds of information returned. Overall, it is complete for its complexity.

  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?

  There are no parameters (schema is an empty object), so the description does not need to explain parameter meanings. The baseline for 0 params is 4, and the description appropriately avoids adding irrelevant parameter details.

  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 function as reporting image provider capabilities, enumerating specific details (providers, defaults, model options, output directory fallback, restrictions). It distinguishes itself from sibling tools (generate_image, edit_image) by being a read-only inspection tool.

  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?

  Provides explicit guidance on when to use the tool: 'Call this first if unsure what is available or why a call failed.' This is helpful, though it does not explicitly mention alternatives or when not to use it, relying on sibling names for differentiation.

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