Server Quality Checklist

Tool Scores

• fuzzy_match_recordsB
  3.4/5.0
  Behavior2/5

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

  There are no annotations, so the description must fully disclose behavioral traits. It only says the tool compares and returns ranked matches, but does not explain the matching algorithm, how the threshold parameter affects results, whether the operation is read-only, or any side effects. This is a significant gap for a tool handling two lists of records.

  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 sentence that gets straight to the point with no filler. It is appropriately concise for a simple tool, though additional details about parameters could be included without harming conciseness.

  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?

  Given the moderate complexity (3 parameters with nested objects) and the lack of output schema or annotations, the description is incomplete. It does not cover return format, threshold semantics, prerequisites, or edge cases. The example is helpful but does not substitute for behavioral or parameter details.

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

  Parameters2/5

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

  Schema coverage is 0%, so the description must add meaning beyond the raw fields. It references 'two lists of records' which loosely maps to source_records and target_records, and the example implies the 'system' field differs across sources. However, the 'threshold' parameter is completely unexplained, and the structure of the records (id, name, system) is not clarified beyond what the schema already shows.

  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 action ('Compare two lists of records and return ranked matches') and specifies the resource ('two lists of records'). It also distinguishes itself from sibling tools by mentioning fuzzy matching and giving a concrete reconciliation example (Salesforce vs SAP, ServiceNow CIs), which implies a matchmaking purpose different from consistency checks or entity registration.

  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 use case ('Ideal for reconciling Salesforce accounts vs SAP customers or ServiceNow CIs'), which tells the agent when to use the tool. However, it does not explicitly mention when not to use it or suggest alternative tools, so it falls short of full guidance.

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

• register_entityA
  3.5/5.0
  Behavior3/5

  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 does disclose that the registration affects future lookups, but it lacks detail on side effects like overwriting behavior, idempotency, or persistence. The core behavior is clear, but deeper behavioral context is missing.

  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 extremely concise, consisting of two short sentences that front-load the purpose and usage. Every word earns its place, with no redundancy or filler.

  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 4 parameters, no annotations, and no output schema, making the description the sole source of guidance. It covers the basic action and when to call it, but omits parameter semantics and potential edge cases, leaving the agent under-informed for a tool with this complexity.

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

  Parameters1/5

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

  Schema description coverage is 0%, yet the description provides no explanations for the parameters (id, name, system, attributes). It doesn't clarify what 'system' refers to or how 'attributes' are used, leaving the agent without sufficient meaning beyond the field names.

  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's purpose: to register a known good entity into resolver memory for future lookups. The verb 'register' is specific and the resource is well-defined, distinguishing it from siblings like resolve_entity or fuzzy_match_records.

  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 phrase 'Call this after a human confirms a match' provides explicit guidance on when to use the tool. It implies not to use it before confirmation, though it doesn't name alternative tools or list when-not scenarios.

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

• list_registered_entitiesA
  3.6/5.0
  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 of behavioral disclosure. It indicates the tool reads current state ('currently registered') and ties to 'agent memory', suggesting a read-only diagnostic operation. However, it does not explicitly state that it has no side effects, nor does it describe pagination, ordering, or return volume. This is minimal but sufficient for a simple list operation.

  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, concise and front-loaded with the primary action. The parenthetical adds a useful use-case without fluff. Every word contributes meaning, and there is no redundancy or unnecessary detail.

  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 simple with only two optional parameters and no output schema. The description conveys the purpose and a use case, but it lacks explicit information about the output format (though 'List' implies returning entities). It also does not mention sorting, pagination limits, or how the limit parameter behaves beyond the default. For a debugging tool, this is adequate but not fully complete.

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

  Parameters2/5

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

  The schema provides descriptions for only one of two parameters (system), leaving limit with a default but no explanation. The description itself does not mention either parameter, so it adds no semantic value beyond the schema. With schema coverage at 50%, the description fails to compensate for the lack of parameter detail, especially for the limit parameter.

  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 action ('List') and the resource ('currently registered entities'), with a specific verb and noun phrase. It is distinct from sibling tools like register_entity (which writes) and resolve_entity/fuzzy_match_records (which look up specific entities). The parenthetical 'useful for debugging agent memory' adds a practical purpose that further clarifies intent.

  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 for debugging agent memory, which gives a clear context but does not explicitly state when to use this tool versus alternatives or mention exclusions. There is no comparison to sibling tools or guidance on when not to use it. The usage guidance is implied rather than explicit.

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

• check_consistencyA
  3.7/5.0
  Behavior3/5

  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 states the check function and gives an example but does not disclose whether the operation is read-only, what output format to expect, or any side effects. This is a minimum viable disclosure for a check-like tool.

  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, focused sentence with no redundancy. It is well-structured, front-loaded with the core action, and contains no filler.

  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?

  For a tool with one parameter and no output schema, the description gives the core purpose but omits expected return values or error conditions. The schema handles the parameter, so the description is sufficient for basic use but not 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 provides a complete description for entity_ids (100% coverage). The description adds context by explaining the purpose but does not add new parameter semantics beyond what the schema already provides.

  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 uses a specific verb 'check' and clearly identifies the resource (logical entity attributes across systems) with a concrete example. It also differentiates from sibling tools like resolve_entity and fuzzy_match_records by focusing on consistency verification rather than resolution or matching.

  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 the tool should be used when you need to verify data consistency across systems, but it does not explicitly mention when not to use it or name alternative tools like resolve_entity. The guidance is implicit rather than explicit.

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

• resolve_entityA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses that the tool returns 'best match + confidence' and implies a read-only nature via 'BEFORE any write', but it doesn't detail behavior on no match, system access, or data modification. This is adequate but not rich.

  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, no fluff. The first sentence states the action and result, the second gives crucial usage context. Every word earns its place.

  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 core purpose, return value (best match + confidence), and critical usage timing. It lacks details like no-match behavior or output structure, but for a resolution tool with 100% parameter schema coverage, this is a solid, near-complete description.

  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 100%, so parameters are already fully described. The tool description adds no additional parameter semantics beyond what the schema provides, thus baseline 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 the tool's function: resolving messy entity names or partial records into canonical matches. It uses a specific verb ('Resolve') and resource ('entity name') and distinguishes from siblings by emphasizing 'canonical match across known systems' and 'Returns best match + confidence', which differentiates it from fuzzy matching tools.

  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?

  Explicitly states 'Use this BEFORE any write or action on customer/account/vendor data', providing clear guidance on when to invoke. It doesn't name alternatives like 'fuzzy_match_records', but the pre-write context effectively distinguishes its use case from sibling tools.

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