Server Quality Checklist

Tool Scores

• kinematic_checkout_statusA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description must carry behavioral information. It clearly frames the operation as a read-only status check and explains the two states, which is useful. It does not disclose what happens for invalid orders, whether anything is mutated, or whether the provision token is returned only after payment.

  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 sentence front-loads the action and outcome states with no filler. Every phrase adds meaning, making the description compact and easy to parse.

  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 single-parameter query tool, the description is mostly complete: it identifies the operation, the input origin, and the two relevant outcomes. It does not detail the response format, but given the absence of an output schema and the simple status domain, this is a minor gap.

  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%, and the order_id parameter already has a clear description: 'the kd- order id from kinematic_checkout.' The tool description adds no additional parameter-level meaning, so the baseline score of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Check') and resource ('Kinematic Drive checkout order') and names the two possible results: pending with pay instructions or paid with provision token. It does not explicitly differentiate itself from sibling tools like kinematic_status, but the status vocabulary and provision-token mention make the purpose reasonably distinct.

  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?

  Usage context is implied: the order_id comes from kinematic_checkout, so the agent can infer this is the follow-up status check after creating an order. However, the description gives no explicit guidance about when to prefer this tool over kinematic_status or when not to use it.

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

• kinematic_statusA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It conveys that the tool is a read-only status check, which is useful behavioral context, but it does not disclose what 'up and running' means, the return format, or any operational caveats.

  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 a single, front-loaded sentence with no filler. It communicates the tool's core purpose efficiently.

  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 status-check tool with one optional parameter, the description is nearly sufficient. It lacks an explicit mention of return semantics or differentiation from similar status tools, but the core usage is clear and no output schema exists to clarify further.

  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%, and the schema already explains the optional 'instance' parameter. The description adds only implicit context that 'instance' refers to a Kinematic Drive instance, which is a marginal addition.

  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 states a specific verb ('Check whether') and resource ('a Kinematic Drive instance is up and running'). It clearly identifies this as a status/health check and distinguishes it from operations like provisioning or checkout.

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

  Usage Guidelines2/5

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

  No guidance is given about when to use this tool versus sibling tools such as kinematic_checkout_status or kinematic_checkout. The context implies a health check, but it does not explicitly state exclusions or preferred scenarios.

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

• janus_askA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It adds meaningful behavioral context by stating that answers are 'grounded on real product knowledge and live data,' signaling reliability and data access. It does not detail response format or failure modes, but the read-only Q&A nature is implied by 'Ask Janus.'

  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 one compact sentence that front-loads the tool's purpose and provides concrete example topics. Every clause adds value and there is no redundant or filler content.

  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?

  The description is adequate for a simple Q&A tool with one required parameter, but it omits explanation of the 'mode' parameter and does not clarify the expected response format. Given the lack of an output schema, a bit more detail about mode behavior would make it fully complete.

  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 coverage is only 50%; the 'question' parameter is described both in the schema and by the tool description, but the 'mode' parameter has no description beyond its enum values and default. The description does not explain what 'human' vs 'agent' mode means or when to use one over the other, leaving a meaningful gap.

  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 the action ('Ask Janus'), the specific resource (UBOS Kinematic Drive concierge), and the exact scope (getting/using a private Kinematic Drive, including pricing, privacy, and connecting an agent). This distinguishes it from the operational sibling tools like kinematic_provision and kinematic_status.

  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 gives clear context for when to use the tool: for questions about getting or using a private Kinematic Drive. It does not explicitly mention alternatives or when not to use it, but the topical scope is sufficiently clear to guide an agent.

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

• kinematic_pricingA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the disclosure burden. 'Get' and 'live source of truth' convey a read-only, current-data operation, but the description does not cover response format, error cases, or network/availability 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?

  A single front-loaded sentence with no filler. Every phrase—'Get,' 'current,' 'live source of truth'—adds meaningful context.

  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 no-parameter read-only lookup, the description is nearly complete: an agent knows what resource is involved and that the data is live/current. The exact return structure is unspecified, but the absence of an output schema and the simplicity of the resource make this 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?

  The input schema has zero parameters and schema description coverage is 100%, so no parameter elaboration is needed. The description's lack of parameter detail is not a gap for a no-parameter tool.

  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 the specific verb 'Get' and identifies the exact resource, 'current Kinematic Drive pricing,' plus the qualifier 'live source of truth.' This clearly distinguishes it from sibling tools focused on provisioning, checkout, and status.

  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 phrase 'live source of truth' implies this tool should be used when current, authoritative pricing is needed, but no explicit when-to-use or when-not-to-use guidance is given. It does not name alternatives or exclusion conditions.

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

• ubos_store_productsA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries full behavioral burden. 'List' clearly signals a read-only operation and 'any agent can pay-per-call' conveys access rules, but the description does not mention whether listing itself costs USDC, what the response format looks like, or whether pagination or filtering is involved.

  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, well-front-loaded sentence states the action, resource, payment model, and two illustrative examples. Every element earns its place, and there is no redundant filler.

  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 parameterless list tool, the description gives the core purpose, examples, and pricing context. It lacks an explicit statement of the return format, but the verb 'List' and the examples make the expected output reasonably clear even without an output schema.

  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 has zero parameters, so there is nothing for the description to clarify. The baseline for zero-parameter tools is 4, and the description adds no unnecessary parameter details.

  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 opens with a specific verb ('List') and a clear resource ('UBOS x402 metered tools'), then gives concrete examples (governor, hotvessel) with prices. This makes the tool's purpose unmistakable and distinguishes it from siblings like ubos_store_call or kinematic_pricing, which are about calling or pricing rather than cataloguing.

  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 the tool is for discovering available metered tools and their costs before purchasing calls, but it never explicitly states when to use it versus alternatives such as kinematic_pricing or ubos_store_call. There is clear context but no exclusionary guidance.

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

• ubos_store_callA
  4.1/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so well: it discloses the pay-per-call cost model, 402 failure behavior, exact payment instructions (USDC on Solana, wallet, memo = api_key), ~15s credit delay, and retry. It also exposes the payload contract for both products.

  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 compact and information-dense; every sentence earns its place. It front-loads the core purpose, then payment behavior, then product payloads, with no filler.

  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 annotations and no output schema, the description covers the essential invocation and payment workflow. It is slightly incomplete about what governor/hotvessel actually return and what a successful response looks like, but the important call/payment semantics are present.

  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 real value by explaining that api_key is an arbitrary agent identity/payment memo and by giving concrete payload examples for governor (action) and hotvessel (prompt), which the schema alone does not provide.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a clear verb+resource: 'Call a UBOS x402 metered tool, pay-per-call,' and gives concrete product examples (governor, hotvessel). It does not explicitly contrast itself with sibling tools, but the pay-per-call framing and payload examples make its role distinct.

  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?

  It communicates the usage context (use when you need to call a metered product and are willing to pay per call) and the retry flow after payment. However, it gives no explicit when-not-to-use guidance and does not mention sibling alternatives such as ubos_store_products or kinematic_* tools.

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

• kinematic_checkoutA
  4.2/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the behavioral disclosure burden. It states that checkout creates an order, that payment happens on-chain via Solana, and that provisioning is asynchronous via polling. It does not discuss idempotency, memo mismatch failures, or order expiration, but the core mutation and required user action are clear.

  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 sentences with zero filler. It front-loads the main action, then provides the payment step and polling follow-up, including an explicit warning about sending the memo exactly as given.

  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 single-parameter tool with no output schema, the description explains the return value (wallet, memo, amount), the follow-up status tool, and the asynchronous provisioning flow. It omits edge cases like invalid memo or order failure, but the essential calling contract is covered.

  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 the single email parameter as the delivery email. The description adds no extra detail about the parameter, matching the baseline for fully covered 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 opens with 'Buy a private Kinematic Drive with USDC', a specific verb and resource, then explains that it creates an order and returns payment instructions. It explicitly contrasts with kinematic_checkout_status, allowing an agent to distinguish checkout from status polling.

  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 a clear workflow: call this to create an order, send USDC with the returned memo, then poll kinematic_checkout_status. It gives concrete context for when this tool is used, though it does not enumerate exclusion criteria or direct alternatives beyond the polling sibling.

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

• kinematic_provisionA
  4.2/5.0
  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 of behavioral disclosure. It clearly states the tool only records a request, does not charge, and does not spin up anything immediately, which prevents misconceptions about side effects. It does not cover auth or rate limits, but for a simple request-recording tool this is sufficient.

  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 long, front-loads the primary purpose, and includes the most important caveat (no charge/spin-up) without any filler. Every sentence contributes to understanding the tool's behavior.

  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 (a request recorder) and full schema coverage, the description is largely complete. It omits what the call returns (e.g., an ID or confirmation), but the existence of a sibling checkout_status tool implies the user tracks progress elsewhere, so for a provisioning request this is adequate.

  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 all three parameters, each with clear descriptions, so the schema already documents them. The description adds no additional meaning about how the parameters should be used together, leaving the baseline at 3 without justification to go higher.

  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 names a specific verb ('Request') and resource ('private Kinematic Drive'), and clarifies it's 'managed onboarding' that only records the request. It distinguishes itself from siblings: checkout likely handles actual delivery and status handles tracking, so the agent can tell them apart.

  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 this is the initial step in a managed onboarding flow ('Records the request; the UBOS team mints an isolated drive for you'), and explicitly states 'No charge or spin-up happens from this call,' signaling it is not the action that creates the drive. However, it does not explicitly name alternatives or conditions for when not to use this tool.

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