Server Quality Checklist

Tool Scores

• smart_crop_previewC
  2.7/5.0
  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 states the tool 'Return' URLs, implying a read-only operation, but does not disclose potential errors, side effects, or what happens if the image does not exist. Without annotations or further detail, the behavioral expectations are largely unstated.

  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, concise sentence with no filler. It is front-loaded with the primary purpose. However, the brevity contributes to under-specification, so while it is efficient, it could use a second sentence to add crucial context without losing conciseness.

  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 has 4 required parameters, no output schema, no annotations, and low schema coverage, the description is insufficient for an agent to use it correctly. It does not explain what the returned URLs look like, how projectName and dimensions are used, or how it differs from related tools. Considerable inference is required.

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

  Parameters2/5

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

  Schema coverage is only 25%, with only 'name' described as 'Stored extension-less image name'. The description adds the phrase 'at specified dimensions' but does not explain how width and height are interpreted, or what projectName refers to. It fails to compensate for the low schema coverage.

  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 function: 'Return crop variant URLs for a given image at specified dimensions.' It uses the verb 'Return' and specifies the resource (crop variant URLs), distinguishing it from sibling tools like audit_lcp or migrate_assets. However, it could more explicitly differentiate from the closely related generate_responsive_tag, so it's not a perfect 5.

  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 implies use for images requiring crop variants at specific dimensions, but does not mention any exclusions, prerequisites, or conditions. Sibling tool names (e.g., generate_responsive_tag) suggest potential overlap, but the description fails to address this distinction.

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

• generate_altB
  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 mentions 'using vision AI' but does not disclose potential side effects, return format, or prerequisites (e.g., public accessibility of the URL). This is a significant gap for a tool with no output schema.

  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 immediately conveys the core purpose. It is well-structured and front-loaded, with no unnecessary words or repetition.

  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 absence of an output schema, the description should explain what the tool returns (e.g., the generated alt text string), but it only states the action. It also omits important context about input requirements, making it incomplete for an agent to anticipate the tool's behavior.

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

  Parameters2/5

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

  The description adds minimal meaning to the single parameter 'imageUrl' by saying 'image URL,' which essentially restates the schema property. With schema description coverage at 0%, the description does not compensate by providing additional context such as accepted formats or URL requirements.

  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: 'Generate accessible alt text for an image URL using vision AI.' It uses a specific verb ('generate') and a specific resource ('alt text for an image URL'), which unambiguously distinguishes it from sibling tools like 'audit_lcp' or 'generate_responsive_tag'.

  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 should be used when alt text is needed for an image URL, but it does not explicitly state when to use it versus alternatives or provide any exclusions. The sibling tools are clearly different, so the context is implied rather than explicitly stated.

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

• generate_responsive_tagB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full burden of disclosing behavioral traits. It states the output (a <picture> element) but does not clarify side effects, such as whether any file is written, whether an external AuraImage service is called, or whether validation occurs. The relationship between inputs (projectName, name) and the 'AuraImage URL' is also unexplained, leaving the tool's behavior largely opaque.

  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 that directly states the tool's purpose. There is no extraneous information, and every word contributes to understanding the core function. It is appropriately concise.

  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?

  The tool is moderately complex (4 parameters, no output schema, no annotations), yet the description is minimal. It does not specify what the generated 'element' looks like (e.g., is it a string?), how the AuraImage URL is derived, or what the return value is. The lack of an output schema further compounds this, leaving the overall behavior and input-output mapping under-specified.

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

  Parameters2/5

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

  Schema description coverage is only 25% (only 'name' has a description), so the tool description must compensate by explaining the parameters. It does not clarify how 'widths', 'alt', 'projectName', or 'name' map to the generated <picture> element, nor how the AuraImage URL is constructed. This leaves significant gaps for an agent attempting to invoke the tool correctly.

  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 specifies the tool's action: generating a <picture> element with AVIF and WebP srcsets. It names the resource (AuraImage URL) and is specific enough to distinguish from sibling tools like generate_alt or smart_crop_preview, which focus on different aspects of image handling.

  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 a responsive <picture> element is needed, but it does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. There is no direct reference to sibling tools, so guidance is only inferred.

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

• audit_lcpA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description must indicate safety. The verbs 'Scan' and 'estimate' imply a non-destructive read operation, but the description does not explicitly state that no files are modified or whether any external dependencies are 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 entire description is one sentence that conveys the core action and purpose. 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?

  The description omits what the tool returns (e.g., a report, list of files, or metrics). Without an output schema, the agent must infer the result format. It also doesn't mention any preconditions or limitations (e.g., npm project, HTML files).

  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 only parameter (directory) is fully documented in the schema with 'Absolute path to the project root'. The description adds no additional semantics beyond the 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 uses a specific verb ('Scan') and a resource ('project directory') with a clear objective ('for unoptimized images') and outcome ('estimate LCP savings'). It is distinguishable from sibling tools that focus on asset migration, alt text generation, responsive tags, and cropping.

  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 a use case (auditing a project for LCP improvement) but does not explicitly state when to use it versus alternatives like migrate_assets or generate_alt. It lacks exclusion criteria or prerequisites.

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

• migrate_assetsA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the burden of behavioral disclosure. It mentions the dryRun preview behavior, which is useful. However, it doesn't disclose potential side effects like whether uploads overwrite existing assets, require authentication, or what happens after upload. The preview hint adds some transparency but leaves 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 two concise sentences, with no redundant information. It front-loads the core purpose and adds a practical tip. Every word earns its place, making it highly efficient.

  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?

  The description is minimal and lacks details about return values, error conditions, or prerequisites (e.g., whether the project must already exist). Since there is no output schema or annotations to supplement, the description carries the full burden. It's sufficient for a simple upload tool but leaves room for more context about the migration behavior.

  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 67%, with 'directory' and 'projectName' described in the schema. The 'dryRun' parameter lacks a schema description, but the tool description explains its purpose ('use dryRun=true to preview'), which adds meaning beyond the schema. This compensates for the missing parameter documentation and clarifies its effect.

  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: 'Upload local image assets to AuraImage.' It uses a specific verb ('upload') and names both the resource ('local image assets') and destination ('AuraImage'). This distinguishes it from sibling tools like audit_lcp or generate_alt, which serve different functions.

  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 gives a usage tip ('Use dryRun=true to preview') but doesn't explicitly state when to use this tool versus alternatives. It implies usage for uploading assets but provides no exclusions or comparison with sibling tools. This is adequate but not explicit guidance.

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