Server Quality Checklist

Tool Scores

• analyze_structureB
  3.2/5.0
  Behavior2/5

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

  There are no annotations describing side effects, read-only behavior, return format, or error cases. The description covers the core function but leaves behavioral expectations implicit.

  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 and front-loaded, with no filler or redundant wording. Every sentence contributes directly to understanding the tool's purpose.

  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?

  For a simple analysis tool, the description conveys the essential purpose and parameter. However, it lacks details about the output format, return value, or potential errors, and it provides no usage context relative to 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?

  The only parameter, path, is described as an absolute path to the project directory. This adds meaningful detail beyond the schema's type and title, though additional constraints or examples would make it even clearer.

  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 summarizes project folder structure—files, languages, folders, and dependency graph scale—using a specific verb ('요약한다'). It is distinguishable from siblings like generate_dependency_diagram or extract_dependency_graph, though it does not explicitly contrast itself with them.

  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 provided on when to use this tool versus the sibling tools, nor are prerequisites or appropriate contexts mentioned. The description only says what the tool does, not when it should be chosen.

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

• generate_dependency_diagramA
  3.6/5.0
  Behavior3/5

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

  The description discloses that the tool returns Mermaid text that can be shown as a code block, which is useful. However, with no annotations provided, it carries the full burden of behavioral disclosure and does not mention side effects, error handling, performance characteristics, or any constraints. It gives some context but lacks depth.

  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 and well-structured, leading with the purpose and then listing parameters clearly. It avoids unnecessary verbosity and front-loads the core functionality, though it could be slightly tighter by removing the redundant instruction about displaying the result.

  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 absence of an output schema and annotations, the description adequately explains the return format and how to use it. It covers all parameters and provides defaults. However, it lacks guidance on error cases (e.g., invalid path) or scale limitations, which might be relevant for an analysis tool, so it is not fully complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  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 thoroughly explains all four parameters: path (absolute directory path), granularity (folder vs. file with default), focus (prefix for drill-down), and direction (TD/TB/LR/RL/BT). This fully clarifies each parameter's meaning and defaults beyond the bare schema.

  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 generates a Mermaid flowchart of module/file dependencies, which is specific and identifies the resource. However, it does not explicitly differentiate from the sibling tool 'extract_dependency_graph', which likely has overlapping functionality, so it falls short of 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?

  There is no guidance on when to use this tool versus the siblings like extract_dependency_graph or analyze_structure. The description only explains what it does, not the conditions that would make it the preferred choice, so 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.

• extract_dependency_graphA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description bears the full burden. It indicates the output format (node-edge JSON) and intended use, but does not disclose side effects, error behavior, or whether the operation is read-only. This is a basic extraction tool, so the lack of detail is moderate.

  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 concise, using two sentences to convey the tool's function and parameter meanings. It avoids unnecessary jargon and is well-structured for quick understanding.

  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 provides essential context: the output is node-edge JSON for reuse, and parameter roles are clear. It lacks an explicit output schema, but for a simple extraction tool, this level of detail is sufficient. Minor gap is the absence of error handling notes or examples, but not critical.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Although the schema properties lack individual descriptions, the main description explains both parameters: 'path' is an absolute directory path, and 'granularity' has a default of 'file' with an option for 'folder'. This covers 100% of the parameters effectively.

  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 extracts a dependency graph and outputs it as node-edge JSON, which is a specific verb-resource combination. It distinguishes from sibling tools like analyze_structure and generate_dependency_diagram by focusing on extraction in JSON format.

  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 mentions the purpose is for reuse/post-processing, but does not explicitly state when to use this tool versus alternatives. It lacks explicit 'use when...' or 'not for...' guidance, leaving the selection somewhat inferred from the purpose.

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

• review_code_qualityA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It transparently states it performs deterministic static analysis (implying read-only), explains that it does not create new judgments but only prioritizes existing signals, and describes how results are communicated. This is strong transparency, though it doesn't explicitly mention side effects or output format beyond 'traffic light'.

  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 concise and to the point, using two sentences to cover purpose, behavior, and parameters. No redundant or vague wording.

  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 that there is no output schema, the description sufficiently conveys what the tool does and the nature of its output (signals explained in plain language with priorities). It could be more explicit about the exact result format, but it's adequate for an agent to understand the tool's functionality.

  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?

  Despite zero schema description coverage, the description explains both parameters: 'path' is the absolute directory to analyze, and 'hub_threshold' is the hub detection connection count threshold with 0 meaning auto-compute. This fully compensates for the schema's lack of detail, adding meaningful context.

  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 structural smells (cycles, hubs, isolation, folder boundaries) and presents them as a traffic light. It also distinguishes itself from LLM-based assessment, providing a specific and unambiguous 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 provides some usage context (deterministic static analysis, not LLM-based) but does not explicitly compare with sibling tools like analyze_structure or extract_dependency_graph. It lacks explicit 'when to use vs alternatives' guidance, so it's only partially helpful.

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