Server Quality Checklist

Tool Scores

• hara_callB
  3.4/5.0
  Behavior3/5

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

  Annotations already indicate it's read-only and non-destructive. The description adds that it runs in a fresh restricted sandbox and that arguments are never concatenated into source, which provides security context. However, it doesn't detail error behaviors, output format, or side effects beyond annotations. It doesn't contradict annotations.

  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, two sentences, front-loaded with the verb 'Invoke' and key context. Every word adds value, no 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?

  With 5 parameters including nested `limits` and a complex recursion, the description lacks sufficient detail. It doesn't explain why `source` is a parameter (seems redundant with 'already-loaded' but maybe it's the source form), or how `limits` affect execution. Output schema exists, but that doesn't cover parameter guidance. The description leaves too much to infer.

  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 description coverage is 0%, and the description doesn't explain any parameters individually. It mentions 'transfer-safe arguments' and 'qualified Hara Var' but doesn't specify what `namespace`, `symbol`, `source`, or `limits` mean. With 5 parameters and many nested, the description should compensate but doesn't.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states the tool invokes a loaded Hara Var with transfer-safe arguments in a restricted sandbox, which is clear and specific enough. It distinguishes from siblings like hara_eval (which likely evaluates expressions) by focusing on calling a pre-loaded qualified variable, though it doesn't explicitly name these differences.

  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?

  It implies this tool is for invoking already-loaded vars, not loading them (distinguishing from hara_runtime_get and hara_eval), and mentions transfer-safe arguments for safety. However, it doesn't provide explicit criteria or when-not-to-use compared to alternatives, though context signals could help.

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

• hara_runtime_getA
  3.6/5.0
  Behavior3/5

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

  The readOnlyHint annotation already indicates this is a non-destructive read operation. The description adds transparency by enumerating the specific data returned (host, build, sandbox profile, limits, availability), which is helpful context but does not go beyond the annotation's safety indication.

  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, concise sentence packed with specific technical terms (execution host, runtime build, sandbox profile, limits, availability). There is no redundancy or fluff; every word contributes to the meaning.

  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 has no parameters and a simple getter role, the description sufficiently conveys what is returned. However, it does not specify the format or structure of the return value, and no output schema is provided, so some ambiguity remains. Still, the core purpose is clear.

  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?

  There are no parameters in the schema, so coverage is 100% by default. The description does not mention any parameters (as none exist), but it also does not add any extra context about how the tool selects the runtime, which could be relevant. Since schema coverage is full, 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 the action ('Return') and specifies the resource (Hara runtime information) with distinct attributes (execution host, runtime build, sandbox profile, limits, availability). This distinguishes it from sibling tools like hara_eval and hara_call, which likely perform evaluations or calls.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus the siblings (hara_eval, hara_call, hara_check). It does not state that this should be called before evaluating or calling, nor does it mention any alternatives. This leaves the agent to infer usage context.

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

• hara_checkA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable context: the check is 'bounded', runs in a 'fresh restricted pure sandbox profile', and returns 'structured diagnostics'. This goes beyond the annotations, though the 'same sandbox profile' reference is slightly ambiguous without knowing what it is the same as.

  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?

  A single, dense sentence that front-loads the action, enumerates the check types, and conveys the key context (bounded, fresh sandbox, structured diagnostics) without wasted words. Every clause adds meaningful information.

  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 description covers the core purpose, check types, sandbox environment, and output nature, and an output schema exists to explain return values. However, it omits the semantics of the `limits` parameter, gives no guidance on error/failure behavior, and the 'same fresh restricted pure sandbox' phrasing is unclear without additional context.

  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 description coverage is 0%, so the description needed to compensate, but it only mentions 'bounded' without explaining the `limits` object or its wallMs/outputBytes fields. It does restate the profile enum values, but those are already present in the schema. The `source` parameter semantics are implied by the title, not detailed.

  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 ('Run') and resource ('check' on Hara source), enumerates the exact check varieties (reader, compile, namespace, lint, test), and clarifies the sandbox context and output type. This clearly differentiates it from sibling tools like hara_eval or hara_call by emphasizing diagnostics-producing checks.

  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 this tool: whenever a bounded compile/lint/test/namespace/reader check is needed. However, it does not explicitly state when not to use it or name alternatives like hara_eval or hara_call, leaving the decision to the agent's inference.

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

• hara_evalA
  4.3/5.0
  Behavior5/5

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

  Annotations already mark readOnlyHint=true and destructiveHint=false, but the description adds crucial behavioral details: 'fresh restricted, no-network, no-browser, non-persistent sandbox' and 'enrolled compatible host.' This goes beyond the annotations and helps the agent understand side effects and prerequisites.

  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 that is front-loaded with the core purpose and environment details. It is concise with no filler or redundant content, earning the highest score for structure.

  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?

  The description covers the execution environment and prerequisites ('enrolled compatible host') but does not explain parameter details, return behavior, or failure modes. Since an output schema exists, return value explanation is less critical, but the absence of parameter guidance creates a minor gap.

  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 description coverage is 0%, so the description must compensate. However, it does not mention 'source' or 'limits' at all. While the schema is self-explanatory for some (source is a string, limits has wallMs/outputBytes), the description adds no meaning, leaving agents to infer parameter semantics from names alone.

  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 the specific verb 'Evaluate' with the resource 'inline Hara source' and clearly states the environment (fresh restricted, no-network, no-browser, non-persistent sandbox). This distinguishes it from siblings like hara_call or hara_check, which imply 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 implies usage for evaluating inline code snippets in a safe, isolated environment, but does not explicitly contrast with alternatives (e.g., when to use hara_call vs hara_eval). The provided context is clear but lacks explicit exclusions or alternative tool references.

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