Server Quality Checklist

Tool Scores

• slice_modelA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It transparently states the paid nature, the exact price tiers for outputs, that omitting payment returns a 402 challenge, and that optional preview/G-code outputs are included only if requested. It does not mention potential timeouts or size limits, but the critical behavioral traits (payment gating, challenge response, optional outputs) are clearly disclosed.

  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 reasonably concise (about 120 words) and well-structured: payment notice, core function, optional outputs, pricing table, input instructions, and auth behavior. Every sentence contributes useful information. The pricing detail is verbose but necessary for a paid tool; it could be slightly trimmed, but overall it is efficient.

  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 complexity (12 parameters, no output schema, no annotations), the description is quite complete. It explains the main return values (print time, filament grams, etc.), optional outputs (preview/G-code), input file formats, and the payment/challenge flow. It does not detail the exact JSON response structure, but that is partly covered by the listed outputs and is not mandatory for basic invocation.

  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 baseline is 3. The description adds high-level context (e.g., file types, price implications of include_preview/include_gcode) but does not provide parameter-specific syntax or details beyond what the schema already documents. It adds marginal value over 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 ('slice') and resource ('3D model') and enumerates the concrete outputs (print time, filament grams, layer count, geometry, fits-on-bed). It clearly distinguishes from sibling tools like list_printers, analyze_model, and get_print_quote by focusing on the slicing action and its result.

  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 context on when to use the tool (to slice a 3D model on a specific printer) and includes essential usage prerequisites (payment via x402, upload STL/3MF/OBJ/STEP). It does not explicitly name alternatives, but the workflow is well explained with the payment challenge behavior, making the intended usage unambiguous.

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

• check_printabilityA
  4.4/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses free vs. paid behavior, the $0.01 USDC cost, x402 challenge flow, the difference between exact and heuristic fields, and how x_payment settles the challenge. This is exceptionally transparent about side effects and requirements.

  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 dense and front-loaded with its core purpose. Every sentence contributes unique information about free/paid features, payment, or use case, though the length is considerable; it is concise for the tool's complexity but not maximally streamlined.

  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?

  For a complex tool with 10 optional parameters and no output schema, the description covers both free and paid modes, expected results, payment challenge behavior, and intended usage context. It is sufficiently complete for an agent to select and invoke the tool correctly.

  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 the baseline is 3. The description adds narrative context for 'full' and 'x_payment' but largely repeats what the schema already states, adding little new parameter-level meaning.

  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 identifies a specific verb ('check') and resource ('3D-print DFM/printability... model') and lists concrete deliverables: printable verdict, watertight check, dimensions, wall-thickness, overhang heuristic. It distinguishes itself from siblings by focusing on DFM/printability rather than slicing or quoting.

  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 explicitly says 'Great before quoting or slicing to catch thin walls, non-watertight meshes, and support-heavy geometry,' which gives clear timing and intent. However, it does not name alternatives or explicitly state when not to use this tool, so it falls short of a 5.

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

• get_print_quoteA
  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 transparency burden. It discloses the exact cost ($0.005 USDC on Base), payment method (x402), and non-payment behavior (returns a challenge). It also emphasizes 'not an estimate' to set accuracy expectations. Some error handling details are missing, but core behavioral traits are well covered.

  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 two sentences deliver all critical information efficiently. The paid status is front-loaded, followed by accuracy claim, outputs, input actions, and the two payment states. Every sentence earns its place with no fluff.

  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 no output schema and 6 parameters, the description explains both call modes (unpaid challenge and paid result), expected outputs (time, grams, quote), and supported input formats. It omits PLY from the input list (though schema allows it) and doesn't detail the exact response structure, but for a quote tool this is adequate.

  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?

  The schema already covers all 6 parameters (100% coverage), so baseline is 3. The description adds meaningful context: automatic volume discounts relate to quantity, material affects material + machine time pricing, and x_payment determines whether a challenge or real result is returned. This goes beyond the schema's individual field descriptions.

  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 title and description clearly state the tool provides a 3D printing price quote. It specifies that it uses a real OrcaSlicer slice (not an estimate) and lists the exact outputs: print time, filament grams, and a priced quote. This distinguishes it from siblings like check_printability or slice_model.

  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 explains the payment workflow: omit x_payment to receive a challenge, include it to settle and get the result. It also tells the user to upload a model. It doesn't explicitly compare to sibling tools, but the purpose is distinct enough that usage context is clear.

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

• analyze_modelA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses the paid nature ($0.002 USDC on Base, x402), payment flow (returns challenge without payment), and that it only performs geometry analysis (no slicing, no side effects). This exceeds typical transparency for read-only tools.

  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 tightly packed with essential info: payment, outputs, and payment behavior. No fluff; every sentence adds value. Front-loaded with the most critical fact (PAID).

  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?

  The tool has no output schema and no annotations, yet the description lists the expected return metrics (bounding box, volume, triangle count, watertight flag, fits-on-bed check) and explains the payment challenge flow. This covers the key context needed to decide when and how to invoke the tool, despite missing explicit error handling details.

  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% for all 5 parameters, so baseline is 3. The description adds minor context (e.g., 'optional printer' for fits-on-bed check, 'without payment' for x_payment), but most parameter meaning is already in the schema. No significant compensation needed.

  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 analyzes 3D model geometry with specific outputs (bounding box, volume, triangle count, watertight flag, fits-on-bed check). It explicitly distinguishes itself from slicing ('Geometry only, no slice') and identifies as a sanity check, setting it apart from sibling tools like slice_model.

  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 as a cheap sanity check before printing and explicitly says 'no slice', which guides away from slice_model. However, it does not explicitly compare with check_printability or optimize_orientation, so it lacks full when-not/alternatives guidance.

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

• list_printersA
  4.7/5.0
  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 discloses that the tool is 'FREE' and 'No payment required', returns 'live' data, and specifies exactly what is included. While it does not explicitly state 'read-only', the verb 'returns' implies a safe discovery operation, and the cost/liveness context adds transparency beyond the minimal.

  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 'FREE' and 'Discovery', and every clause adds specific detail about the returned data. There is no filler or repetition.

  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?

  The description thoroughly details the return payload (12 printers with fields, 12 materials, pricing tiers), explains the 'call first' purpose, and notes cost. Even without an output schema, the description fully compensates by enumerating the exact items and their purpose.

  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?

  The input schema is empty, so the baseline is 4. The description adds value by explaining that the tool outputs printer and material IDs specifically for use in other tools, which gives the agent context for parameter selection in subsequent calls, even though this tool itself has no parameters.

  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: it lists the 3D printer fleet, materials, and pricing tiers. It uses the specific verb 'returns' and names the resources, and distinguishes itself from siblings by positioning this as the initial discovery step before quoting, slicing, or DFM checks.

  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?

  The description explicitly instructs to 'Call this FIRST' to choose printer and material IDs before using quoting, slicing, or DFM check tools. This provides clear when-to-use guidance and differentiates it from downstream sibling tools.

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

• optimize_orientationA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully bears the burden of behavioral disclosure. It reveals the payment requirement, the 402 challenge behavior, the fact that it performs multiple real slices, and that results are exact and slice-derived. It also discloses the benefit (reduces waste, time, post-processing) and the specific output of savings vs. as-is orientation.

  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 four dense sentences, each adding essential information: paid nature, core function, benefits, reason for cost, and payment flow. It is front-loaded with the most critical detail (PAID) and avoids wasted words while remaining complete.

  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?

  For a complex paid tool with 9 parameters and no annotations or output schema, the description covers the main behavioral aspects: payment, what the tool does, why it costs more, and what the user gets (recommended orientation and savings). It adequately compensates for missing structured metadata.

  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?

  The schema has 100% parameter coverage, so baseline is 3. The description adds meaningful semantics for x_payment (forwarded as X-PAYMENT header), explains the difference between model_url and model_base64, and clarifies infill_percent's role in a full DFM report, which goes beyond the schema. However, many parameter details are already in 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 clearly states the tool's function: optimize 3D-print orientation by slicing up to 4 candidate orientations with supports and recommending the one using the least support material. It distinguishes itself from sibling tools like slice_model by focusing specifically on support minimization and reporting savings versus the as-is orientation.

  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 explains the paid x402 flow (returns challenge without payment, requires x_payment to settle) and notes it costs more than other tools because it runs multiple slices, implying when cost is a consideration. It does not explicitly name alternatives or state when not to use, but the context of optimizing support waste is clear.

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