Server Quality Checklist

Tool Scores

• get_record_schemaA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It says "Return" implying read-only, and notes it is a deliberate duplicate, but does not explicitly state safety, auth requirements, or idempotency. It adds the context of the duplicate resource, which is useful.

  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 concise sentences, front-loaded with the main action, and includes a relevant implementation note without fluff.

  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 parameterless schema getter, the description fully covers its purpose, content, and the reason for existing (duplicate of a resource). No additional context is needed given the simplicity.

  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?

  There are zero parameters, so the schema is empty. The description adds value by explaining what the tool returns (fields, types, rules), satisfying the baseline for no-parameter tools.

  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 ("Return") and identifies the resource ("asset-record.json contract") and the content (fields, types, rules). It also distinguishes from siblings like read_record by focusing on schema rather than data or finalization.

  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 states a specific use case ("a client with no resource support") and points to an alternative resource (`record://schema`). It doesn't explicitly contrast with sibling tools but the purpose is clear enough.

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

• record_factsA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses deep-merge behavior, return format (merged record plus missing fields), and error responses on rejection. However, it doesn't explain what causes rejection or prerequisites like whether a record must already exist, leaving some behavioral gaps.

  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 concise—three sentences covering purpose, usage pattern, and exclusions—with no wasted words. It is front-loaded with the primary purpose. Slight downside is that the return format is crammed into the second sentence, making it dense, but overall 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 the tool's complexity (nested patch object, no output schema, no annotations), the description provides sufficient context: when to call, what to include, what to avoid, and what to expect in the response. It misses directory semantics and error code specifics, but it is complete enough for an agent to select and invoke 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?

  Schema description coverage is 0%, so the description must compensate. It explains the 'patch' parameter by listing acceptable fact fields (language, framework, etc.) and explicitly excludes author fields. However, the 'directory' parameter is not explained at all, and no details are given about value formats or required structure.

  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 records creation facts (language, framework, runtime, dependencies, repository identity, timestamp) and explicitly distinguishes from sibling finalize_record by excluding author-only fields. The verb 'Record' plus resource specification leaves no ambiguity about its function.

  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?

  Explicit guidance is provided: 'call it as often as facts arrive' and a direct exclusion—'Do NOT use this for created_by, maintained_by or model_access.mode -- those are the author's to confirm via finalize_record.' This clearly indicates when to use the tool and when not, referencing the alternative tool.

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

• read_recordA
  4.4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden. It discloses the exact return shape, the error format, and explicitly states that a missing file is a normal state, not an error. This is full behavioral 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 three sentences, each serving a distinct purpose: what the tool does, the return format, and error/missing-file behavior. It is front-loaded and contains no redundant information.

  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 tool with no output schema, the description fully covers the return structure and error cases. It appropriately notes that a missing file is normal, preventing potential misinterpretation. The only gap is the directory parameter, but that is already accounted for in parameter semantics.

  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 has one parameter 'directory' with default '.', but the description does not mention it at all. With schema description coverage at 0%, the description should clarify how the directory parameter relates to reading the asset-record.json, but instead it only says 'current asset-record.json', leaving ambiguity about the parameter's role.

  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 reads the current asset-record.json and reports missing author-only fields. The verb 'Read' and resource 'asset-record.json' are specific, and the action is distinct from sibling tools like get_record_schema or finalize_record.

  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 conveys clear context: use to read the record and see which author-only fields are missing. It does not explicitly compare to sibling tools or state when not to use, so it gets 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.

• finalize_recordA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden. It discloses side effects ('Writes a confirmation block'), failure behavior ('rejection writes nothing at all'), and specific rejection conditions (missing/blank confirmation or invalid record). This is thorough behavioral transparency.

  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 three sentences and front-loaded with the core action. It packs significant detail (confirmations, modes, side effects, return values) without excessive verbosity. Slightly longer than necessary but every sentence contributes value.

  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 state-changing operation with no output schema, the description is fairly complete: it explains success and error return shapes, prerequisites, and side effects. The only notable omission is the `directory` parameter, which is not explained, and there is no explicit mention of how the tool fits with sibling tools.

  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 0%, but the description adds substantial meaning for the key parameters: it explains `confirmations` (must contain created_by, maintained_by, model_access.mode) and `mode` (conversation vs elicitation, with elicitation ignoring confirmations). However, the `directory` parameter is not mentioned at all, leaving a gap in the otherwise strong parameter explanation.

  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 action: 'Mark the asset record complete, before the first push.' This is a specific verb+resource+timing that distinguishes it from siblings like read_record, get_record_schema, and record_facts, which are all read-only or schema-related.

  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 clear context for when to use the tool ('before the first push') and explains the two modes (conversation and elicitation). It does not explicitly name alternatives, but the read-only siblings clearly do not perform finalization, making the usage context sufficiently clear.

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