Server Quality Checklist

Tool Scores

• verify_receiptA
  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 burden of behavioral disclosure. It does reveal that verification is Ed25519-based and requires the original signed bodies, which implies a read-only cryptographic operation. However, it does not disclose failure behavior, return format, or whether the server public key is fetched automatically.

  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 focused sentences with no filler. The primary action is front-loaded, and the input instruction is concise without repeating the schema.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema, no annotations, zero parameter descriptions, and nested objects, but the description only covers the basic verification intent and input roles. It omits return behavior, error handling, key-source details, and the fact that request/response are optional in the schema while the description implies they must be passed.

  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 coverage is 0%, so the description must compensate. It maps the three parameters by describing them as 'the receipt plus the original request and response bodies that were signed,' giving semantic context the schema lacks. It does not describe the internal structure of any nested object, so the agent still lacks construction 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?

  States a specific verb ('Verify'), a precise resource ('an Ed25519 ScreenVerity receipt'), and the target ('the server public key'). This clearly differentiates it from sibling tools like screen and sources.

  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 when to use the tool by saying it verifies a receipt and asking for the original signed request and response bodies. However, it does not explicitly state when not to use it or mention alternatives, so the agent must infer usage context.

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

• sourcesA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses that this is a listing operation, that sources may have never been loaded, and what fields describe their state. While it does not mention side effects or auth, 'List' implies a read-only operation and the coverage caveat adds useful behavioral context.

  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 compact sentence that front-loads the action and resource, lists the return fields efficiently, and ends with a practical usage hint. No filler or redundant repetition.

  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 simple, optional-parameter list tool with no output schema, the description is complete: it names the resource, the fields returned, and the recommended calling context. Nothing essential 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.

  Parameters3/5

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

  The single optional parameter jurisdiction is fully described in the input schema with an example. The description itself adds no parameter-level meaning, so the schema coverage earns the baseline score of 3.

  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 action (List), a precise resource (exclusion/license sources currently loaded by ScreenVerity), and enumerates the returned fields. This clearly distinguishes it from the sibling tools screen and verify_receipt, which perform different operations.

  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 explicit context for when to call it: 'Call before assuming a state is covered.' It does not name alternatives or state when not to use it, but the sibling tools are sufficiently different that this is minor.

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

• screenA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden and does well: it discloses the structured-match return plus Ed25519 receipt, the token-cost advantage, no-API-key availability, and the meaning of possible_match. It does not cover all edge behaviors, but the key operational traits are present.

  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 front-loaded with the core purpose. Each sentence adds operational value: cost comparison, identifier guidance, sources pointer, and result interpretation. There is 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?

  For a tool with nested subject/options, no annotations, and no output schema, the description covers the main usage concerns: what it screens, how to improve matches, where to get list info, cost, authentication, and how to interpret possible_match. It could add options parameter semantics, but the core context needed to select and invoke the tool is present.

  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 usefully says 'Always pass npi, dob, or license when known,' which adds meaning to the subject identifiers. However, it says nothing about the options.lists or options.min_confidence parameters, leaving part of the request surface unexplained.

  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 and resource: 'Screen a person or organization against maintained U.S. exclusion/debarment and selected license lists.' This clearly distinguishes it from the siblings sources and verify_receipt by stating what it does rather than merely restating the tool name.

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

  Usage Guidelines5/5

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

  It gives explicit when-to-use guidance: prefer this over browsing state portals, read sources first to know loaded lists, and always pass npi, dob, or license when known. This routes the agent to the right workflow and identifies the main alternative without ambiguity.

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