Server Quality Checklist

Tool Scores

• check_addressA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint and non-destructive, and the description adds meaningful behavioral detail beyond that: the exact return semantics (risk score 0-100, bands, categories), conditional verbosity with an API key, and the resource cost ('Each call consumes one check'). It doesn't contradict annotations, and the additional consumption caveat is valuable.

  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 front-loaded with the purpose and returns, then use cases, then chains and consumption. It is concise at four sentences, with no fluff. It could be slightly tighter (the chain list is redundant with the schema enum), but it remains efficiently structured and readable.

  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 the presence of an output schema, the description need not detail return types, but it still explains the risk score range, band concept, and categories. It also covers supported chains, use cases, and the API-key enhancement. Everything an agent needs to invoke and interpret the result is present, so it is fully complete.

  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 input schema already provides full descriptions for both parameters (chain enum and address format), so the baseline is 3. The description adds no extra parameter semantics—it only references the chain coverage implicitly, which the schema already communicates. No additional meaning is introduced beyond 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 begins with a clear verb-resource pair ('Score a single crypto address for AML and compliance risk') that precisely states the tool's function. It also differentiates from the sibling tool screen_transaction by focusing on address-level vetting rather than transaction screening.

  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 lists concrete use cases ('before sending funds', 'triage a pasted address', 'vet a deposit address'), giving clear context for when to use it. It does not explicitly exclude transaction screening, but the single sibling tool makes the distinction evident; mentioning that tool as an alternative would make this a perfect 5.

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

• screen_transactionA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context beyond annotations: 'Each call consumes one check from the configured traql account' (a quota side effect) and describes the return structure ('score, band, flags and itemized signals'). This is consistent with annotations and provides useful operational detail.

  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?

  Well-structured with a clear opening statement followed by a bulleted breakdown of modes. The information is front-loaded and each sentence serves a purpose—no filler or redundancy. It is slightly long but contains only necessary details, earning a 4 rather than 5 due to the length.

  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 the tool's complexity (two modes, six parameters, chain restrictions, and an existing output schema), the description covers all essential usage context: modes, which chains support which mode, use cases, and the quota side effect. Nothing critical is missing for an agent to invoke it correctly.

  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 meaning by explaining the two modes and how parameters relate (pre-flight: from/to, optional amount/asset; by-hash: tx_hash only, mutually exclusive). It also gives an example for the amount format, reinforcing the schema description. This is helpful clarification beyond the schema's individual 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 opens with a clear verb+resource: 'Screen a transaction for AML and compliance risk by scoring both sides.' It explicitly differentiates from the sibling address-check tool by focusing on transactions and even references the shared return format ('same score, band, flags and itemized signals as an address check'). This leaves no ambiguity about what the tool does and how it differs from check_address.

  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 clearly states when to use it: 'Use it as a pre-send safety gate, or to review a payment that already went out.' It also details two explicit modes with the exact parameters to pass ('pass from and to...' vs 'pass only tx_hash') and lists chain support for each. While it doesn't explicitly name check_address as an alternative, the mention of 'same... as an address check' implies routing, so guidance is strong but not exhaustive.

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