Server Quality Checklist

Tool Scores

• fillA
  4/5.0
  Behavior4/5

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

  The description discloses key behaviors: deterministic, no network call, shape constraints (e.g., do not repeat first point for freeform). It also explains differences between stadium and rectangle with cornerRadius, and between polygon and freeform. Missing details on error handling or output format.

  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 covers a lot of information, which is concise. However, it could benefit from better structure (e.g., bullet points) to improve readability given the complexity.

  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 the complexity (7 parameters, nested shapes) and no output schema, the description lacks information about return values or file format. The schema provides good internal descriptions, but the description could offer more guidance on integrating with sibling tools.

  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 main description adds minimal parameter semantics beyond the already rich schema descriptions. The schema covers most parameters with detailed explanations (e.g., stadium vs rectangle, freeform usage). The description's contribution is marginal, 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 tool generates a solid plug to fill holes/cavities, lists all supported shapes (circular, rectangular, stadium, polygon, freeform), and specifies it's deterministic CadQuery without network calls. This sufficiently distinguishes it from sibling tools like caps and meshes.

  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 usage contexts by stating it takes structured JSON (no image) and is deterministic. However, it does not explicitly state when to use this tool over siblings or when not to use it, though the sibling tool names give some differentiation.

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

• repair_meshA
  4.3/5.0
  Behavior4/5

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

  Details repair actions (removing non-manifold edges, filling holes, unifying normals, remeshing). No annotations exist, so description carries full burden; covers key behaviors but omits potential downsides like quality loss.

  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 sentences, front-loaded with main purpose and inputs. Every sentence adds value; no 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?

  Covers all inputs (URL, base64, format), operations, outputs (STL/base64 + summary). No output schema, but description sufficiently explains return value. Complete for a repair tool with 7 params.

  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 100%, so baseline 3. Description adds minimal extra semantics beyond schema; e.g., repairLevel options deferred to field description. Adequate but not enhanced.

  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 repairing 3D meshes to be manifold/watertight/print-ready, with specific operations listed. Distinguishes from sibling tools (generate, fill) by focusing on repair.

  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?

  Describes when to use (e.g., from generate_visual_mesh or local CadQuery). Does not explicitly exclude other tools or state when not to use, but context implies repair for flawed meshes.

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

• generate_precise_capA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It states 'deterministic CadQuery, no network call,' which is helpful for safety and behavior. However, it does not disclose potential side effects (e.g., if any files are modified) or output format specifics.

  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 sentences, front-loaded with purpose, then constraints, then behavioral info. Every sentence adds value with no wasted words.

  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?

  The description covers the tool's purpose and constraints well, but does not specify how to choose output format (STL vs STEP) or if an additional parameter is needed. Given the lack of output schema, this 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?

  Schema description coverage is 100%, so baseline is 3. The description adds meaning beyond schema by clarifying input format (JSON only, no image), and alludes to default values for parameters like threadDepth and threadStarts, enhancing understanding.

  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 generates a threaded cap STL/STEP from measured opening dimensions, specifying the resource (threaded cap) and action (generate). It distinguishes from sibling tools (fill, generate_visual_mesh, repair_mesh) which have different purposes.

  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 explicitly says it 'takes structured JSON only (no image)' and that vision/dimension extraction happens client-side before calling this tool, clarifying when to use it. It does not explicitly state when not to use it, but sibling context makes the distinction clear.

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

• generate_visual_meshA
  4.4/5.0
  Behavior4/5

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

  No annotations provided, description carries full burden. Discloses output is STL, non-precise, uses external API. Lacks details on permissions, rate limits, or side effects, but sufficient for core behavior.

  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 sentences: primary action, usage guidance, post-processing instruction. Each sentence is essential, no redundancy, front-loaded with purpose.

  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 one-parameter tool with no output schema, description covers purpose, output type, precision limitation, and next steps. Missing details on input constraints (e.g., image format) but otherwise complete.

  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% for the single parameter (imageBase64). Description adds no extra meaning beyond 'raw image', 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 explicitly states 'Generate a 3D mesh from a raw image' and specifies output as STL. It distinguishes from siblings by noting it is not suited for precision parts, contrasting with generate_precise_cap.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides clear when-to-use ('for visualization only') and when-not-to-use ('not dimensionally precise, not suited to a cap/plug that needs to physically fit'). Also directs to feed into repair_mesh, guiding post-usage.

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