Server Quality Checklist

Tool Scores

• amlA
  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 must carry the transparency burden. It discloses the return values (risk score, band, sources, flagged participants) and the credit cost behavior, including that actual credits appear in response headers. However, it does not explicitly state that the operation is read-only, nor mention rate limits or latency, so some behavioral traits remain undisclosed.

  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 well-structured with action bullets, return summaries, and a credit cost note. It is a bit longer than strictly necessary but each section adds meaningful information, particularly the cost warning which is valuable for an agent deciding to invoke the tool. No filler or redundant repetition of schema details.

  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?

  Given there is no output schema or annotations, the description sufficiently explains what each action returns and provides important cost context. The action-based parameter requirements are clearly communicated through the bullet descriptions, making the tool self-contained and usable for an agent without additional external knowledge.

  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 structured schema already documents all five parameters. The description adds only minimal parameter context, such as which action uses which parameter (e.g., address for verify-address), but this is already implied by the schema descriptions. No additional semantics are needed, so the baseline of 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 that the tool performs AML risk checks for addresses and transactions, and enumerates two specific actions (verify-address, screen-transaction) with distinct purposes and outputs. This makes it easy to distinguish from the only sibling tool, system_info.

  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 each action: verify-address for checking a blockchain address, screen-transaction for screening a transaction. It also highlights the significant credit costs, which helps an agent weigh cost against need. However, it does not explicitly rule out when not to use the tool or compare to alternative tools beyond the implicit sibling distinction.

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

• system_infoA
  4.8/5.0
  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 explicitly notes 'no API call, no credits consumed,' which is key behavioral information. It also discloses detailed content such as retry strategy, HMAC security, and rate-limit penalty multipliers, going well beyond a generic 'returns info' statement.

  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 critical 'no API call, no credits consumed' caveat and uses a compact bullet list. Each bullet covers a distinct action without wasted prose, making it highly scannable for an agent.

  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 reference-documentation tool with no output schema and no annotations, this description is complete enough: it defines all five actions and gives sufficient detail about their content. It also clarifies side effects (none) and cost implications (none), covering the main contextual risks.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Although schema coverage is 100%, the description adds significant meaning by explaining each allowed action enum value in detail (e.g., callbacks covers URL requirements, 5 retries, HMAC). This transforms enum names into actionable context and compensates fully beyond the schema's short parameter 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 description states this is CryptoAPIs reference documentation with no API call or credits consumed, and enumerates five specific topics (blockchains, errors, credits, callbacks, limits). This clearly identifies it as an informational tool distinct from domain siblings like aml.

  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 bulleted actions give clear contexts for when to use the tool, such as looking up error codes, credit structures, callback mechanics, or rate limits. It does not explicitly name alternatives or exclusion conditions, so it stops short of a full when/when-not specification.

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