Server Quality Checklist

Tool Scores

• get_agent_manifestA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden for behavioral disclosure. It notes the tool is 'free' and describes it as a catalog, implying a read-only informational nature, but it does not explicitly state that it has no side effects, or discuss permissions, rate limits, or return behavior. This is adequate but 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 the key directive 'Start here', and contains no filler. Every phrase contributes meaningful information (contents, next step), making it highly concise and well-structured.

  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 there is no output schema and no annotations, the description does a good job of explaining what the tool returns by listing the manifest contents (catalog of 3 terminal tools, value_proposition_v1, use_scenarios_v1, glossary_v1) and the recommended follow-up. It is slightly cryptic with versioned names but sufficient for an agent to use the tool effectively.

  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 fully documents the only parameter (locale) with its allowed values and default, and the description does not add any additional meaning. Since schema coverage is 100%, the baseline of 3 applies, and the description adds no extra value for parameters.

  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 the tool as an entry-point manifest cataloging 3 terminal tools plus supporting documents, distinguishing it from siblings by instructing to start here and then call get_liq_radar. It uses 'Start here' as the verb, which implies retrieval of a catalog, and lists specific contents, making the purpose clear even if not a conventional verb like 'get' or 'list'.

  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 states when to use this tool ('Start here') and provides a direct next step ('Then call get_liq_radar for the forced-order map'). This gives clear sequencing but does not mention when not to use it or alternatives like swap_via_nattswap, so it falls short of a full 5.

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

• swap_via_nattswapA
  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 behavior: it returns a route and suggests actions, emphasizes 'MCP read-only until wallet signs', and notes gas and integrator fees. This gives the agent an accurate picture of side effects and costs, exceeding typical 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 compact but information-dense, with sections for purpose, use cases, return values, and side effects. Every sentence serves a distinct purpose, and there is no fluff or repetition. The structure is easy to parse despite the all-caps emphasis.

  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 swap tool with no output schema, the description covers essential context: what is returned (route, readiness, actions), how to proceed (sign actions in order), cost implications (free MCP, on-chain fees), and side effects (read-only until signing). This is complete enough for an agent to act safely and effectively.

  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 description coverage is 100%, so each parameter is already well-documented. The description adds high-level context (e.g., 'Prefer signing swap_actions_v1 in order') but does not elaborate on individual parameters. Baseline 3 is appropriate because the schema carries the burden, and the description provides no additional per-parameter semantics.

  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 performs a 'cross-chain token swap powered by Li.Fi across 70+ chains', using a specific verb and resource. It also highlights Hyperliquid support, distinguishing it from siblings like get_liq_radar. This leaves no ambiguity about the tool's core function.

  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?

  Explicit 'USE WHEN' list provides concrete scenarios (bridge, fund gas, treasury routing, rebalance), giving clear context for when to invoke. It stops short of naming specific alternatives or when not to use, so it earns a 4 rather than a 5.

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

• get_liq_radarA
  4.6/5.0
  Behavior5/5

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

  No annotations exist, so the description carries full burden. It discloses cost ($0.001 x402 Base or Solana), network options, default symbol behavior, whitelist constraints, return type, and explicitly states 'Side effects: none.' This is comprehensive behavioral disclosure.

  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 front-loaded with the tool's identity and payload, then systematically covers whitelist, use cases, exclusions, return, cost, and side effects. Every sentence provides distinct, non-redundant 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, the description conveys the essence of the return (hypernatt_liq_radar_v2) and lists its components. It also covers cost, payment, and side effects. However, it doesn't detail the structure of the output or interpret the indicators, leaving some ambiguity for an agent, but overall sufficient for a data-retrieval 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?

  Schema coverage is 100% and includes detailed descriptions for all three parameters. The description adds the cost amount and network flexibility ('Base or Solana') not present in schema, and reinforces symbol whitelist/default. However, agent_wallet parameter is not discussed in the description; schema already covers it, so the added value is moderate.

  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 tool as a forced-order/liquidation map with specific deliverables (magnet bias, OI build-up, L/S ratio, clusters, real liqs). It distinguishes from siblings (get_agent_manifest, swap_via_nattswap) by stating it reveals market structure that 'classic public indicators do not show' and explicitly states it returns a specific radar (hypernatt_liq_radar_v2).

  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?

  Provides explicit usage context ('USE WHEN: terrain / timing / sizing context') and negation ('NOT a trade signal or Fuel Score'), but does not name alternative tools or explicitly compare with siblings. This is clear guidance but lacks explicit alternative references, so not a 5.

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