Server Quality Checklist

Tool Scores

• validateB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that no code is executed and explicitly labels the tool safe for untrusted claims, which are key behavioral traits. However, it omits the expected return format, error behavior, and any side effects (beyond implying read-only). This is adequate but not comprehensive for an unannotated 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 two concise sentences with zero waste. The core purpose and safety disclaimer are front-loaded, and argument types follow immediately. Every phrase earns its place.

  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, but with no output schema, the description should explain what a successful or failed validation looks like (e.g., return value). It also omits any assumptions about file existence or claim format constraints. Given the tool's narrow scope, it's moderately complete but leaves the agent guessing about results.

  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 100%, so both parameters are already documented. The description restates 'claim (claim JSON text)' and 'claim_path (absolute file path)' without adding new meaning beyond the schema. It clarifies the input types but adds marginal value over the existing parameter descriptions.

  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 clearly states the tool checks a claim's structure and anchor/frozen hashes without executing code. It uses a specific verb ('Check') and names the resource. While it doesn't explicitly contrast with siblings (self_test, verify), the safety note and 'WITHOUT executing any code' hint at differentiation, making the purpose unambiguous.

  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 context (safe for untrusted claims) but gives no guidance on when to use this tool versus alternatives like verify or self_test. There is no mention of exclusions or prerequisites, leaving the agent to infer appropriate usage from name alone.

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

• self_testA
  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 of behavioral disclosure. It does disclose the return shape (passed/exit_code/output), which is useful, but it says nothing about whether the operation is safe/side-effect-free, whether it requires any setup, or how to interpret the passed/exit_code fields. For a zero-parameter self-test this is acceptable but minimal.

  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 short clauses with zero filler. The action verb is front-loaded and the return format is stated in a compact second clause. Every word earns its place; nothing is redundant.

  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 tool is trivial in complexity: zero parameters, no annotations, no output schema, no nested objects. The description covers what it does, why it exists, and what it returns. The only minor gap is a potential note on how to interpret exit_code/passed beyond the raw field names, which is a small omission for an otherwise simple tool.

  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?

  The tool has zero parameters, which sets a baseline of 4 per the rubric. Schema coverage of properties is trivially 100% with an empty object, so there is nothing for the description to add about parameters. The description instead correctly documents the return format, which is more valuable here.

  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?

  States a specific action ('Run the gate self-test') on a clear resource and adds purpose ('proves the tool works in this environment'). It is implicitly distinct from the sibling tools validate and verify, since it tests the environment/tool itself rather than validating some external input. Loses a point only for not explicitly contrasting with those siblings, but the purpose is unambiguous.

  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?

  No guidance on when to call this tool versus the siblings validate or verify. There is a weak implication (use it to prove the environment works) but no explicit when-to-use, no exclusions, and no mention of whether this should be run before other tools or as a diagnostic. 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.

• verifyA
  4.7/5.0
  Behavior5/5

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

  The description explicitly discloses that executing repro.script as arbitrary code with no sandbox carries security risk, and that it requires a permission flag. This is critical behavioral information beyond what annotations would provide (and no annotations are present, so the description carries full burden). It also states the refusal condition, fully disclosing the tool's execution behavior.

  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 long, with the most critical information (execution risk and requirement) front-loaded. Every sentence adds value: what it does, the critical requirement, and the trust caveat. No filler or repetition of schema details.

  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 tool with three parameters, no output schema, and no annotations, the description covers the essential context: what it does, the dangerous execution behavior, the mandatory flag, and a safety warning. The only minor gap is not describing the return value, but since there's no output schema, the description could have stated what it returns; however, the primary usage risks are fully covered, and the tool is a verification action where the result is likely self-evident. Given the high stakes, this is comprehensive.

  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 schema already documents each parameter's type and purpose. The description adds clarifications: allow_execution must be true and is required, claim and claim_path are alternatives for specifying the claim. It doesn't add syntax examples or detailed formats, but given the schema is complete, this is adequate. The description reinforces the critical flag without redundancy.

  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 performs 'full verification of a claim' and explicitly mentions executing its repro.script as arbitrary code with no sandbox, which is a specific, high-stakes action. It also names its core requirement (allow_execution=true) and contrasts with siblings like validate and self_test by emphasizing execution, distinguishing it clearly.

  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 includes explicit conditions: 'REQUIRES allow_execution=true; otherwise refused' and 'Only call this on claims you trust.' This provides clear when-to-use guidance, though it doesn't explicitly name alternatives like validate or self_test as safer options. The context is strong enough for an agent to infer the trade-offs, but a direct comparison would improve it.

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