Server Quality Checklist

Tool Scores

• classify_complexityA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description must carry the burden of behavioral disclosure. It does so by specifying the active profile (claude) and the list of available profiles, as well as the return fields (tier, effort, suggested model, confidence, reasoning). This gives the agent insight into the tool's behavior and output structure. It does not explicitly state side effects (e.g., read-only, cost implications), but for a classification tool this is largely implied. The description adds meaningful behavioral context beyond a simple statement of purpose.

  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 sentences, front-loaded with the primary purpose, then efficiently lists profiles and return fields. Every clause adds useful information: the active profile, alternative profiles, and what the tool returns. There is no redundant phrasing or filler. It is concise yet comprehensive for the tool's scope.

  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?

  With no output schema, the description appropriately lists the return fields (tier, effort, suggested model, confidence, reasoning). It also covers the profile parameter and its active default. While it doesn't explain the meaning of each return field in depth or describe edge cases, it is complete enough for an agent to understand what the tool does and what it will receive. The given context (2 parameters, 1 required) is well covered, making this a solid 4.

  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 coverage is 100%, so the baseline is 3. The description adds significant value by explaining the profile parameter's semantics: 'Active profile: claude (Anthropic native model IDs (haiku / sonnet / opus)). Profiles: claude, openrouter-cost, openrouter-balanced.' This clarifies the enum values and the meaning of the active profile, which the schema only lists as names. The prompt parameter is self-explanatory. The description enhances parameter understanding beyond the schema, justifying a 4.

  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 primary function: 'Classify a prompt's complexity and return the optimal model tier + thinking effort.' This is a specific verb (classify) with a specific resource (prompt complexity) and a well-defined outcome, making the purpose unmistakable. Even without sibling tools to differentiate, the description is precise and covers both the action and the deliverable.

  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—classifying a prompt to determine model tier and effort—but does not explicitly state when to use it versus alternatives or when not to use it. It provides context about profiles and return fields, but there is no direct guidance on deployment scenarios or exclusions. The usage is implied rather than explicitly instructed, yielding a score of 3.

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