Server Quality Checklist

Tool Scores

• review_changesA
  3.5/5.0
  Behavior2/5

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

  With no annotations, the description bears the full burden of disclosing behavioral traits. It reveals that the tool uses an external AI service (OpenAI Codex) but does not mention important traits like non-destructiveness, network/cost implications, privacy considerations, or what the output looks like. The two-mode behavior is useful but insufficient.

  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 that front-load the core purpose and quickly explain the two operational modes. Every sentence adds value, with no unnecessary words or repetition.

  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 explains the core functionality and two usage modes, and the schema covers all parameters. However, with no output schema and no annotations, the description is incomplete regarding what the tool returns, potential side effects, and external service implications. It is adequate but leaves clear gaps.

  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 100% coverage with clear descriptions for all four parameters, so the baseline is 3. The description reinforces the diff vs. all-files distinction relevant to the 'type' parameter but does not add additional semantic meaning beyond what the schema already states.

  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 reviews code using OpenAI Codex and distinguishes it from retrieval-only sibling tools by specifying it works on git diffs or all files in plain directories. The verb 'review' plus the two operation modes give a precise, specific purpose.

  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 (for code review) and explains the two modes (git repos vs. plain directories), but it does not explicitly contrast it with get_diff or get_changed_files, nor does it state when not to use it. This is useful contextual guidance but lacks explicit alternatives or exclusions.

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

• get_changed_filesA
  3.8/5.0
  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 a key non-obvious behavior: in plain directories, files are listed with an 'added' status. This goes beyond a simple 'list files' statement. Lacks details on side effects or return format, but for a read-only listing tool this is a moderate gap.

  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, well-structured sentence with no redundancy. The opening verb is direct, and the conditional clause adds critical differentiation without bloat.

  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?

  Without an output schema or annotations, the description leaves important operational gaps: what counts as a 'source file', whether the list is recursive, and what the default 'type' is when omitted for git repos. It covers the two main modes but is not sufficiently complete for an agent to invoke the tool confidently in all cases.

  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%, and both parameters have descriptions. The tool description adds contextual nuance (e.g., that 'type' only matters for git repos and that plain directories always list as 'added'), but it does not provide additional syntax or format details beyond the schema. 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?

  States a clear verb ('List'), resource ('files'), and scope ('changed files' in git, 'all source files as added' in plain directories). This distinguishes it from siblings like get_diff (which likely returns diffs) without needing to name them.

  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?

  Provides context that the tool behaves differently for git repos versus plain directories, implying when it is useful. However, it does not mention alternatives (e.g., get_diff, review_changes) or give explicit when-not-to-use guidance.

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

• get_diffA
  4/5.0
  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 adds meaningful context by stating that git repos yield 'git diff' while plain directories return 'file contents in unified diff format'. However, it does not explicitly mention read-only nature, potential error conditions, or any dependencies (e.g., git being installed), leaving some gaps.

  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 compact two sentences with the primary action front-loaded. It efficiently conveys the tool's dual behavior without unnecessary details, earning every word.

  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 simple tool with well-documented parameters and no output schema, the description covers the key contextual nuance of git versus non-git behavior. It is adequate but could be more explicit about the output type (e.g., a text string), so it does not reach full completeness.

  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 100% coverage for all three parameters with clear descriptions, including the 'type' enum's git-only usage. The description adds no additional parameter semantics beyond what the schema already specifies, so the baseline score 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 tool's function: 'Get diff output' with a specific resource (diff). It further distinguishes behavior for git repos versus plain directories, differentiating it from sibling tools like review_changes and get_changed_files, which handle review and file listing respectively.

  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 about usage by explaining what happens in git repos versus plain directories, helping the agent decide when to use it. However, it does not explicitly name alternatives or state when not to use the tool, so it falls short of full usage guidance.

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