Server Quality Checklist

Tool Scores

• gdlintC
  2.8/5.0
  Behavior2/5

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

  没有任何 annotations，描述承担了全部行为披露责任。但描述只说了“检查”，未说明是否只读、是否修改文件、输出格式、退出码、错误处理等行为。对于无 annotation 的工具，这种透明度明显不足。

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  描述只有一句话，非常简短且没有冗余，但考虑到工具无 annotations、无输出 schema，这样的篇幅显得过于单薄，不足以支撑正确调用，属于“简洁但不够充分”。

  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?

  工具包含 3 个参数、无 annotations、无输出 schema，描述却只有一个动作说明，缺少使用场景、行为约束和结果说明。上下文信息不足以让 agent 在没有额外知识的情况下正确判断调用后果。

  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?

  input schema 对三个参数的描述覆盖率为 100%，已经说明了 project、file 的绝对路径要求以及 all 的默认值。描述本身没有补充参数含义，因此基于 schema 完整覆盖给予基线 3 分。

  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?

  描述包含了明确的动词和资源：“运行 gdlint 检查 GDScript 文件”，表明这是一个 lint 检查操作。虽然未明确与其他兄弟工具区分，但 gdlint 的专有名称和“检查”语义足以让 agent 初步判断用途。

  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?

  描述没有说明何时使用 gdlint 而不是其他兄弟工具（如 godot_check_all、godot_get_errors），也没有给出选择条件或排除场景。仅从语义上暗示用于 GDScript 文件检查，缺乏明确的工具路由指导。

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

• gdformatC
  2.9/5.0
  Behavior2/5

  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, and it fails to deliver. '格式化' implies rewriting files, but the description never discloses that running this tool actually modifies the user's source file in place (given check defaults to false), nor does it mention idempotency, prerequisites (gdformat installation), or side effects. The schema hints at mutation via the check param, but the description itself is silent on behavior.

  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, efficient sentence with zero fluff or redundancy. It is appropriately front-loaded with the primary action. The brevity is more a symptom of under-specification on other dimensions than a conciseness defect.

  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?

  For a tool that mutates source files, this description is too thin. It lacks usage guidance, behavioral transparency, and tool-selection context, and there is no output schema to fill in return-value expectations. The schema covers parameters well, but an agent gets no help on when to invoke this versus siblings or what consequences (in-place file rewriting) to expect.

  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 all three parameters (file, check, project) are already documented with meaningful descriptions such as absolute-path requirements and the check flag's 'don't actually modify' semantics. The description adds nothing about parameters, but the baseline of 3 applies because the schema does the heavy lifting.

  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 a specific verb ('格式化'/'format') and resource ('GDScript 文件'), making the core purpose immediately clear. Formatting is implicitly distinct from the sibling tools' lint/check/validate operations, though it never names or contrasts a sibling explicitly. It leans slightly tautological by saying 'run gdformat' when the tool is already named gdformat, which keeps it just below a 5.

  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 zero guidance on when to use this tool versus the sibling alternatives (gdlint, godot_check_all, etc.). No context, no exclusions, and no hint about when formatting is appropriate versus linting or checking. An agent must infer entirely from the tool name and schema.

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

• godot_export_validateC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full behavioral burden. It does not disclose whether export is actually run, whether files are modified, whether external tools are invoked, or what the validation result contains. 'Check' hints at a read-only operation but is not explicit.

  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 concise sentence with no filler and the main action is front-loaded. It loses a point because its brevity omits useful context that could reasonably fit in one or two more phrases.

  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 no output schema and no annotations, the description is too thin for safe invocation: it does not explain what happens when the tool runs, what the output looks like, or how it relates to sibling tools. The simple parameter list helps, but the behavioral and usage gaps remain significant.

  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 schema already documents both parameters with 100% coverage, including the preset default and the absolute-path requirement. The description adds no additional meaning beyond the schema, so the baseline score applies.

  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 identifies a specific verb ('check') and object ('dependency errors') and names the mechanism ('Godot export validation'). It is clear about the tool's purpose, though it does not explicitly distinguish it from siblings like godot_get_errors or godot_check_all.

  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 is given about when to use this tool versus alternatives such as gdlint, gdformat, godot_check_all, or godot_get_errors. The agent must infer the appropriate context from the tool name and description.

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

• godot_get_errorsC
  2.9/5.0
  Behavior2/5

  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 not explain how errors are retrieved, what 'recent' means, whether the log_file parameter affects behavior, whether this is a read-only operation, or what side effects might occur.

  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, efficient sentence with no redundancy. It could be slightly more informative, but as a concise statement it earns its place and is front-loaded.

  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 no output schema and no annotations, the description should clarify what is returned and under what conditions the tool is useful. It mentions recent error information but leaves the return format, log_file semantics, and relationship to sibling tools unspecified, making it incomplete for an agent to confidently invoke.

  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%, and the description adds no parameter semantics beyond what the schema already documents. With full schema coverage, the baseline of 3 applies; the description's mention of 'recent error info' hints at the log_file usage but does not add explicit parameter-level meaning.

  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 a specific verb ('解析并返回') and resource ('最近的错误信息'), making the tool's core purpose clear. It does not explicitly differentiate from siblings like godot_check_all, which may also report errors, so it loses one point.

  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 is given on when to use this tool versus sibling tools such as gdlint, gdformat, godot_check_all, or godot_export_validate. The description only states what it does, not when it is the appropriate choice or what prerequisites apply.

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

• godot_check_allB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It reveals that the tool performs lint, format, and export, but does not say whether 'format' may rewrite files, whether an export actually generates artifacts, whether steps stop on failure, or what the result/return looks like. This is a significant gap for a composite 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, front-loaded sentence that communicates the core purpose and scope immediately. The parenthetical enumeration of lint, format, and export is compact and informative with no wasted words.

  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 is a composite of several behaviors, has no output schema, and no annotations, so the description must carry more context. It omits return values, side effects, execution order, and failure behavior, leaving an agent without enough information to reliably invoke it for a full project check.

  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%, with descriptions for both 'project' and 'file' parameters. The tool description adds no additional semantics about how the optional file parameter scopes the check or how the project root is used, so it stays at the baseline for high schema coverage.

  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 states a specific action ('执行') on a specific resource ('Godot 项目检查') and enumerates the exact components: lint, format, and export. This distinguishes it as the aggregate check tool alongside siblings gdlint, gdformat, and godot_export_validate, since those correspond to individual pieces of the advertised check.

  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 components list implies this tool is for a full combined check rather than running gdlint, gdformat, or godot_export_validate individually. However, it never explicitly states when to choose this tool over its siblings, nor does it mention prerequisites like export presets or project setup.

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