Server Quality Checklist

Tool Scores

• prepare_image_requestC
  2.7/5.0
  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 states that the tool does not contact the provider, which is a key behavioral trait (non-mutating). However, it does not describe the output format (e.g., whether it returns the JSON payload, any validation results, or errors). For a preview tool, this basic information is valuable but incomplete, as it leaves uncertainty about what exactly will be returned.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness2/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence and is front-loaded, but it is severely under-specified for a tool with 17 parameters and no annotations. It lacks any structural breakdown or elaboration on usage, output, or behavior. The brevity is not conciseness but rather an omission of critical information. A tool of this complexity requires a fuller description.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness1/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (17 parameters), lack of annotations, no output schema, and low schema coverage, the description is woefully incomplete. It provides only a high-level purpose without any context about how to use the parameters, what the preview looks like, or how it relates to generate_image. This is insufficient for an agent to correctly invoke the tool with meaningful parameters.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is only 18%, meaning the schema leaves 82% of parameters undocumented. The description provides zero parameter details, failing to compensate for the low coverage. With 17 parameters, the lack of any explanation about parameters such as 'n', 'size', 'model', 'stream', etc., leaves the agent unable to construct a valid request without external knowledge. The description adds no semantic value beyond the schema's minimal annotations.

  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: 'Preview the outgoing JSON without contacting the provider.' It uses a specific verb ('preview') and resource ('outgoing JSON'), and distinguishes itself from sibling tools like generate_image by indicating it does not contact the provider. This is a clear and unambiguous purpose statement.

  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 offers no explicit guidance on when to use this tool versus alternatives. It does not mention that this should be used before generate_image to validate requests, nor does it provide any exclusions or conditions. The context of 'without contacting the provider' implies a dry-run use case, but that is not stated explicitly. No alternatives are referenced, so the agent must infer the usage pattern.

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

• generate_imageA
  3.5/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of disclosing safety and side effects. It does disclose side effects (preserving response, saving files to disk, returning MCP content). However, it does not reveal potential write/modification behavior, provider-specific limitations, or error-prone conditions like overwriting files or moderation implications.

  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 sentence that is reasonably concise and front-loaded with the main action. It covers multiple behaviors compactly. It could be slightly more structured (e.g., split into purpose and usage), but it earns its place without padding.

  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 18 parameters, no output schema, and no annotations, the description is underspecified for full autonomous use. It clarifies the file-saving and response-preservation behaviors but does not explain the full output contract, provider coordination, or parameter interactions, making it adequate but with clear gaps.

  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 low (22%), so the description partially compensates by clarifying key behavior around save_directory and response preservation. It adds meaning beyond the schema for the main flow, especially the user-selected directory semantics, but leaves many parameters unexplained (e.g., background, moderation, stream, custom_parameters).

  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 uses specific verbs ('Generate', 'preserve', 'save', 'return') and identifies the core resource (image) and key behaviors (file saving, MCP content return). It is clear enough to distinguish from siblings like list_image_providers or get_image_capabilities, though it doesn't explicitly name those 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 the tool is the main generation action, and mentions preserving URL/b64_json response and saving to a user-selected directory, which signals when file persistence is involved. However, it does not provide explicit when-to-use vs. alternatives, prerequisites (e.g., provider selection via prepare_image_request), or exclusions.

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

• list_remote_image_modelsA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must convey behavior. It states it is a read operation ('Read') and clarifies it is not a generation request, but provides no further details on output format, side effects, or requirements, leaving the agent with minimal behavioral insight.

  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 two short sentences that front-load the purpose and add a distinguishing note. 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?

  For a simple list tool with one optional parameter and no output schema, the description is adequate but does not mention the provider filter or the nature of the returned list. Since the schema covers the parameter, this is a minor gap, so a middle score is warranted.

  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%, and the provider parameter includes a helpful reference ('Provider id from list_image_providers'). The tool description itself does not add parameter information, but the schema fully documents it, so baseline 3 is appropriate.

  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 action ('Read the live model list') with a specific resource, and explicitly distinguishes it from a generation request with 'This is not a generation request.' This separates it from sibling tools like generate_image.

  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 (to read available models) and gives a negative guideline by stating it is not a generation request, but does not explicitly mention when to use it relative to alternatives like list_image_providers or get_image_capabilities.

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

• get_image_capabilitiesA
  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 must disclose behavioral traits. It only says 'Show' which implies a read operation, but it does not explicitly state that it is safe, side-effect-free, or has no permission requirements. It also does not mention any potential rate limits or error conditions. This is a significant gap for an unannotated 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 a single, concise sentence that front-loads the key information. Every word contributes to the purpose without fluff, making it highly efficient.

  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 simple read-only tool with one parameter and no output schema, the description sufficiently conveys what is displayed (models, modes, limits, parameters). It does not over-explain and is complete given the tool's simplicity, though it could mention the default provider or output format for extra clarity.

  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?

  The schema already provides full coverage for the single parameter (provider) with a description referencing list_image_providers. The tool description adds no additional meaning beyond the schema, so it meets the baseline for 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 shows supported models, modes, limits, and parameters for a selected provider. This is a specific verb+resource combination that distinguishes it from siblings like list_image_providers (lists providers) and generate_image (creates images).

  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 (when you need provider capabilities) but does not explicitly contrast it with alternatives or state when not to use it. It lacks explicit exclusions or named alternatives, so it is adequate but not explicit.

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

• list_image_providersA
  3.8/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the behavioral burden. "Without exposing credentials" is a meaningful safety trait and adds value beyond the tool name, but it does not disclose return format, potential errors, or whether any privileged access is needed.

  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 one short, front-loaded sentence with no filler. Every word earns its place, and the key security caveat is included without bloating the text.

  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 zero-parameter list operation, the description is mostly complete: it states what is listed and a critical constraint. However, there is no output schema and the description does not specify what fields or identifiers are returned, which is a minor gap.

  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 input schema has zero parameters, so the baseline is 4 per the rubric. The description needs to add no parameter-level detail because there are no parameters to document.

  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 uses a specific verb and resource: "List configured providers" clearly names the action and object. It also adds the credential-safe qualifier, which differentiates it from sibling tools like list_remote_image_models.

  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 gives no guidance on when to choose this tool over siblings such as list_remote_image_models or get_image_capabilities. No alternatives or exclusions are mentioned, so the agent must infer usage purely from the name and short description.

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

• get_image_usageA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral disclosure burden. It clearly states the operation is a read ('Read') and has no image-generation side effect ('without generating images'), which is the key safety-related behavior. However, it omits details about response format or potential errors, though the tool is simple.

  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 a single, front-loaded sentence with no wasted words. It conveys the action, the resource, and the critical non-generation behavior efficiently.

  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 simple tool with one optional parameter and no output schema, the description plus schema covers the essential information: what it reads and what it avoids doing. It lacks an explicit description of the returned usage data, but 'usage' and the endpoint reference provide reasonable context for an agent.

  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?

  The schema already provides 100% coverage for the single parameter 'provider,' including its default and a description pointing to list_image_providers. The tool description adds no additional parameter meaning, so the baseline score of 3 is appropriate.

  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 uses a specific verb 'Read' and identifies the resource as 'the optional usage endpoint,' clearly stating what the tool does. The phrase 'without generating images' explicitly distinguishes it from the sibling tool generate_image.

  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 this tool is for checking usage information rather than performing generation, which provides clear context. It does not explicitly name alternative sibling tools or provide exclusion criteria, but the non-generating framing and provider reference from list_image_providers offer sufficient guidance.

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