Server Quality Checklist

Tool Scores

• decompose_promptA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It discloses the AI vs heuristic behavior and that the return value includes both a summary and full JSON. However, it does not mention limitations like prompt size, rate limits, or error conditions, leaving some gaps.

  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 concise and front-loaded with the main action. It uses a clear two-paragraph structure. The 'Args' and 'Returns' sections add minor redundancy but overall the text is efficient and focused.

  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?

  Given the tool's simplicity (one param, output schema exists), the description covers the key points: how it works (AI vs heuristic), what it produces (structured blocks), and how to use the result (edit or pass to compile_prompt). It does not list block types but references a sibling tool, which is acceptable.

  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 coverage is 0%, so description must compensate. It adds 'The raw prompt string to decompose', which clarifies the parameter's role. However, this is minimal—no examples, length constraints, or formatting hints. For a single simple parameter, this is adequate but not exemplary.

  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: 'Decompose a raw prompt into structured blocks'. It specifies the action (decompose) and resource (raw prompt), and hints at the output format. This distinguishes it from siblings like compile_prompt, which does the reverse.

  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 mentions when to use AI vs heuristic fallback based on configuration, and suggests the output is 'ready to edit or pass to compile_prompt'. It does not explicitly state when not to use, but the sibling context and the decomposition vs compilation contrast provide adequate guidance.

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

• compile_promptA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description should disclose behavioral traits; it mentions the output (XML prompt with token estimate) but does not cover side effects, permissions, or error behavior, leaving some 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 concise (5 sentences plus structured Args/Returns), with the core purpose in the first sentence, and no unnecessary 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?

  Given the tool's simplicity (1 parameter, no enums) and presence of an output schema, the description covers the input format and output summary adequately, though 'Claude-optimized' could be elaborated.

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

  Parameters5/5

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

  The input schema only provides a title and type, but the description thoroughly explains the parameter's format (JSON-stringified list of blocks) with field details, fully compensating for the 0% 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 explicitly states it compiles blocks into a Claude-optimized XML prompt, and references decompose_prompt to differentiate from siblings like list_block_types.

  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?

  It indicates the tool is used after decompose_prompt or with manually crafted blocks, providing clear context for when to invoke it, but does not explicitly exclude other scenarios.

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

• list_block_typesA
  4.5/5.0
  Behavior4/5

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

  With no annotations, description carries full burden. Discloses that it returns descriptions and recommended canonical ordering, and that it is a list operation, which implies no side effects.

  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?

  Three concise, front-loaded sentences with no waste. Every sentence adds value.

  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 low complexity and existence of output schema, description sufficiently covers purpose and return structure. No 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?

  No parameters, so baseline 4. Description does not need to add parameter info.

  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?

  Clearly states 'List all available block types' with specific verb and resource. Distinguishes from sibling tools compile_prompt and decompose_prompt by indicating its use case for manual block crafting.

  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?

  Explicitly states when to use: 'when manually crafting blocks to pass to compile_prompt.' Provides clear context, though does not mention when not to use.

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