Server Quality Checklist

Tool Scores

• carry_healthB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It does not state whether the operation is read-only, what it returns, or any side effects, leaving the agent without critical safety and behavior context.

  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 extremely concise, consisting of only a few words. It efficiently conveys the core purpose, though 'FREE' is arguably extraneous and the lack of structure makes it slightly less polished.

  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 tool is low-complexity with no parameters, but there is no output schema, so the description should specify what the response looks like. It does not mention return format or error behavior, leaving a gap for agents relying solely on this description.

  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 tool has zero parameters, so there is nothing to document. The description does not add parameter details, but the empty schema means no additional explanation is needed, matching the baseline for parameterless tools.

  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 clearly indicates the tool's focus on service health and data freshness, distinguishing it from sibling tools. Although it lacks an explicit verb like 'check' or 'get', the intent is clear and not a tautology.

  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?

  No explicit usage guidance is provided. The purpose implies it is for checking health status, but there are no stated exclusions or comparisons to alternative tools, making it only implicitly useful.

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

• carry_universeA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does disclose a notable trait: the tool is paid (~$0.01 USDC) and the data is sorted by daily notional volume. However, it does not explicitly state whether it is read-only, whether it requires authentication, or what the response format looks like, leaving gaps in transparency.

  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 sentence that front-loads the most critical information (cost) and then concisely states the resource and its attributes. No wasted words or redundant details.

  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 provides a reasonable picture of what the tool returns: the liquid perp universe sorted by daily notional volume, including open interest, mark price, and funding. With no output schema, it defines the core data content. However, it does not mention pagination, result limits, or the exact response structure, which would be helpful but not essential for a simple list tool.

  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 tool has zero parameters, so the schema is fully covered and the baseline is 4. The description adds meaning by naming the data fields (open interest, mark price, current funding) that the tool returns, which compensates for the lack of any parameter detail. No further parameter semantics are needed.

  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 clearly identifies a specific resource (the liquid Hyperliquid perp universe) and specifies its contents (sorting, fields). It indirectly differentiates from sibling tools like carry_snapshot or carry_history by focusing on the full universe. However, it lacks an explicit action verb such as 'fetch' or 'list', which would make the purpose more direct.

  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?

  The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions or comparison with sibling tools like carry_snapshot or carry_rankings. The only context is what the data is, not the use case.

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

• carry_rankingsA
  3.8/5.0
  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 prominently discloses a cost of ~$0.05 USDC and specifies the use of trailing 14d mean funding annualized. It does not mention rate limits or error behavior, but the cost disclosure and calculation details are valuable traits beyond what schema shows.

  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, dense sentence that packs multiple pieces of information: cost, live scope, calculation window, output weights, and a parameter hint. It is front-loaded with the cost warning, making it efficient though slightly dense to parse.

  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 no output schema, the description does enumerate response contents (rank, long/short leg, dollar-neutral weights, spread outliers). However, it omits any explanation of min_volume, a parameter with a default of 0. Without this, the agent may not know how to set the filter, leaving a clear gap for a two-parameter tool.

  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 schema has 2 parameters with 0% description coverage. The description adds meaning for k ('coins per leg' with range 1-20), but min_volume is completely unmentioned. Since half the parameters are undocumented, the description only partially compensates for the schema's lack of description.

  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 provides a full live cross-sectional funding-carry ranking across all liquid Hyperliquid perps, with specific output components like rank, long/short leg weights, and spread variants. This distinguishes it from sibling tools such as carry_snapshot or carry_history by emphasizing cross-sectional coverage.

  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 when a cross-sectional ranking is needed and explains how to adjust k for the number of coins per leg. However, it does not explicitly compare to sibling tools like carry_snapshot or carry_history, so the agent must infer when alternatives are more appropriate.

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

• carry_historyA
  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 reveals the cost ('PAID (~$0.02 USDC)'), the data source ('carrydesk's own published snapshots'), and the timeframe ('archived'), which are key behavioral traits. It does not detail return format or failure modes, but for a simple historical data retrieval, this is sufficient transparency.

  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 exactly two sentences: the first front-loads the cost and the core functionality, the second gives a practical usage guide. Every word earns its place, with no redundancy or filler. The structure is highly 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?

  For a tool with only two parameters, no annotations, and no output schema, the description adequately covers the essential purpose, cost, and usage scenario. It doesn't describe return values or pagination, but those are not critical given the tool's simplicity and the lack of an output schema requirement. The sibling context is implicit in the use-case wording.

  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 0%, so the description must compensate. It refers to 'one coin' which aligns with the required 'coin' parameter, but it does not explain the 'days' parameter beyond the schema's default. Since the parameters are simple and the description at least hints at the coin concept, it provides minimal added value but not enough to fully cover the 0% schema 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 states the tool provides 'Archived rank and trailing funding history for one coin', which identifies both the resource (rank and trailing funding history) and the scope (one coin). The verb 'Use to check' clarifies the intended action. This distinguishes it from siblings like carry_snapshot (current data) and carry_rankings (rankings across coins).

  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 a specific use case: 'to check whether a coin's carry is persistent or a one-day artifact.' This implies using it when you need historical context rather than a current snapshot. It doesn't explicitly mention alternatives or when not to use it, but the sibling context and the specificity of the use case provide clear guidance.

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

• carry_methodA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It adds context by mentioning 'caveats that matter before anyone trades' and notes the tool is 'FREE'. However, it does not explicitly disclose whether the tool has side effects, the nature of its return value, or any limitations beyond referencing caveats. It is not misleading, but it lacks rich behavioral detail.

  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 the core purpose. Each clause adds value: what it explains, key topics, and a caveat about use. No filler or tangential 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 no output schema and no annotations, the description covers the essential context: what the tool is about, why it matters, and when to use it. It mentions specific aspects (universe filter, lookback, leg construction) and flags caveats. It does not explicitly state what the return format will be, but for a 'method' tool, the content is adequately outlined.

  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 tool has zero parameters, and the schema is empty with 100% coverage (nothing to describe). According to the rubric, 0 params defaults to baseline 4. The description does not add parameter-specific meaning because there are none, so no deduction applies.

  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 'How the carry ranking is computed', specifying the content (universe filter, lookback, leg construction). This clearly distinguishes it from sibling tools like carry_rankings (which likely provide rankings) and carry_snapshot (which provides data snapshots). It answers not just what but also the scope of the tool.

  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 usage directive: 'Read this before presenting the numbers as actionable.' This tells the agent when to use the tool relative to other carry tools. It does not explicitly name alternatives or exclusions, but the timing requirement is explicit and actionable.

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

• carry_snapshotA
  4.5/5.0
  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 explains cost (FREE), data latency (Delayed 24h), and output structure (top 5 coins on each leg with long/short definitions), which is substantial for a zero-parameter tool. It lacks details about return format or limits, but nothing contradicts the description.

  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?

  Two sentences, front-loaded with 'FREE' and immediately stating the core purpose. Every clause provides useful information: cost, resource, scope, legs, spread, delay, and usage recommendation. No wasted words.

  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 tool with no parameters and no output schema, the description is fully complete: it explains what data it returns (top coins, spread), the latency, the cost, and the intended use order. An agent can decide to invoke this tool without any additional context.

  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?

  There are zero parameters, so the baseline is 4. The description adds value by explaining the concept of funding-carry and defining the long/short terms, which helps an agent understand what the snapshot means even without 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 what the tool does: provides a cross-sectional funding-carry snapshot for Hyperliquid perps, listing the top 5 coins per leg plus the carry spread. It uses a specific noun phrase and precise scope, distinguishing it as the entry-point snapshot among siblings.

  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 advises 'Use this first,' providing clear context that this is the initial tool to call before diving into more specialized siblings. It does not explicitly name alternatives or exclusions, but the recommendation is unambiguous.

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