Server Quality Checklist

Tool Scores

• review_generated_styleA
  3.7/5.0
  Behavior3/5

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

  Annotations already signal readOnlyHint=true, so the agent knows this is a safe read-only operation. The description adds that the tool checks invariant matches, drift, and violations, which is useful context, but it does not disclose return formatting, limitations, or operational behavior beyond what the output schema and annotations already imply. 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?

  A single front-loaded sentence conveys the core action, target, reference, and review criteria with zero filler. Every word contributes meaning, making it appropriately sized and easy to parse.

  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?

  Despite the tool's high complexity (5 parameters, a massive required styleResult object, output schema), the description offers no workflow guidance—such as first obtaining a StyleTrace via analyze_website_style—and no hints about viewport usage or input exclusivity. The output schema may cover return values, but operational context is under-specified for an agent to use this tool reliably.

  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 0%, so the description must compensate. It only broadly maps generated HTML/image URL and styleResult, but does not explain the viewportWidth/viewportHeight parameters, the enormous required styleResult structure, or the relationship between generatedHtml and generatedImageUrl (e.g., whether one is required). This is insufficient for a tool with 5 parameters and a deeply nested 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?

  Description uses a specific verb ('review') and clearly identifies the target resources (generated HTML or image URL), the reference ('StyleTrace result'), and the criteria (invariant matches, drift, likely style violations). This distinguishes it from the sibling analyze_website_style, which would likely produce the StyleTrace rather than consume it.

  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 clearly implies when to use the tool: after a StyleTrace result exists and when a generated artifact needs validation. It doesn't explicitly state when not to use it or name alternatives, but the 'against a StyleTrace result' framing provides clear contextual separation from the analysis sibling.

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

• analyze_website_styleA
  4.3/5.0
  Behavior4/5

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

  The readOnlyHint annotation already marks this as a safe read operation, and the description complements it by adding key behavioral details: it does not crawl additional pages, analyzes only provided references, and can omit evidence, export to a sidecar file, or inline it. No contradiction with annotations; the added context goes beyond what annotations provide.

  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 compact sentences, each earning its place. It front-loads the core action and output, then adds important constraints and evidence-mode flexibility without waste or redundancy.

  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 six-parameter schema with 100% coverage, an output schema, and readOnly annotations, the description is complete enough for correct invocation. It clearly states what the tool does, what inputs it accepts, and key behavioral constraints (no crawling, evidence modes). No critical information is missing.

  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 six parameters fully, including enums and per-parameter descriptions. The tool description repeats the idea of URLs/images and evidence modes but does not add meaning beyond the schema's own parameter descriptions. 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 uses a specific verb ('Analyze') with a clear resource ('exact public website URLs, public image URLs, or a mix') and states the produced output ('compact design grammar'). It also distinguishes itself by noting StyleTrace analyzes only provided references, which differentiates it from the sibling tool 'review_generated_style'.

  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 usage context: analyze exact public URLs or image URLs to extract design grammar. It also communicates an important constraint ('analyzes only the references you provide') and hints at evidence-mode choices. However, it does not explicitly mention when to prefer this tool over the sibling 'review_generated_style' or state exclusions such as private/internal URLs.

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