Server Quality Checklist

Tool Scores

• delete_edgeA
  3.5/5.0
  Behavior2/5

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

  No annotations provided. Description only mentions 'soft delete' without explaining implications (e.g., reversibility, logging). No disclosure of side effects, idempotency, or error 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?

  Two concise sentences plus bulleted args. No fluff. Front-loaded with 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?

  Covers main functionality and param relationships. Lacks detail on output schema, behavior when no match, or handling multiple matches. Output schema exists but not referenced.

  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?

  Adds meaning beyond schema: explains edge_id overrides other params, and source/target/relation are for conditional deletion. Schema coverage is 0%, so description compensates well.

  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?

  Description clearly states it deletes edges (soft delete) and specifies two modes: by edge_id or by source/target/relation conditions. Distinguishes from sibling tool delete_node by focusing on edges.

  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 explicit guidance on when to use direct vs conditional deletion, nor when not to use. Does not mention prerequisites or alternative tools.

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

• update_nodeA
  3.6/5.0
  Behavior3/5

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

  The description discloses important behaviors: summary and category are fully replaced, add_aliases append, properties merge, and empty strings mean no change. However, it does not mention return values, side effects, or idempotency. With no annotations, the burden is higher.

  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 structured as an Args list with a clear purpose first. It is reasonably concise, though the repeated '빈 문자열이면 변경 안 함' could be condensed without loss.

  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 lack of annotations and schema coverage, the description covers all parameters and their behaviors adequately. However, it does not describe the output or any safety/authorization context, leaving some completeness gaps for a mutation tool.

  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?

  Despite 0% schema coverage, the description thoroughly explains each parameter: purpose, behavior with empty string, and examples for add_aliases and properties. This adds significant meaning beyond the input 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 '특정 노드의 속성을 수정합니다' (modifies properties of a specific node), which is a specific verb+resource. It distinguishes from siblings like delete_node and merge_nodes by implying a single-node update, but could be more explicit about when to use update_node vs merge_nodes.

  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 use this tool vs alternatives (e.g., merge_nodes). The description does not provide context for when not to use it or mention prerequisites.

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

• delete_nodeA
  3.7/5.0
  Behavior4/5

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

  Discloses soft delete behavior and cascade parameter effects. With no annotations, the description carries the full burden and adequately covers key behavioral traits.

  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?

  Extremely concise: two sentences and parameter docs. Front-loaded with the main action, no wasted words.

  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 presence of an output schema and sibling context, the description is mostly complete. It could mention error cases (e.g., node not found), but covers the core behavior well.

  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?

  With 0% schema coverage, the description adds meaning to both parameters: name (the node to delete) and cascade (behavior when edges exist). This compensates for the lack of schema 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 it deletes a node with soft delete, distinguishing it from siblings like delete_edge (edge deletion) and update_node (modification). However, it does not explicitly contrast itself with other siblings.

  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 use this tool versus alternatives (e.g., merge_nodes or update_node). The description lacks context for decision-making.

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

• ingest_knowledgeA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits such as idempotency, error handling, side effects (e.g., overwriting existing nodes), or authorization requirements. The description merely states 'save' without elaboration.

  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 relatively concise with a clear structure: a purpose statement followed by an Args section. However, it mixes Korean and English, which may reduce clarity for international users. Slightly more verbose than necessary but still efficient.

  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 thoroughly covers parameter semantics with examples, addressing a key gap from missing schema descriptions. However, it lacks behavioral context (e.g., idempotency, validation) and assumes an output schema exists but doesn't detail return values. Overall adequate but not comprehensive.

  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?

  The schema coverage is 0%, but the description adds rich, detailed documentation for all three parameters, including examples of JSON format for entities and relations and explanation of raw_text for logging. This greatly exceeds the schema's minimal type information.

  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 'Save knowledge to the graph' and specifies it receives Entity/Relation JSON from Claude, clearly indicating the verb and resource. It distinguishes from sibling tools like delete_node or update_node.

  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 usage for ingesting knowledge extracted by Claude but does not explicitly state when to use versus alternatives or provide exclusion criteria. Context is clear but lacks guidance on when not to use.

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

• list_nodesA
  4.2/5.0
  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 that the tool lists nodes with filtering and pagination, and implies read-only behavior via '조회' (inquiry). It does not mention permissions or side effects, but for a listing tool, the level of detail is adequate.

  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 paragraph with a brief summary followed by a clear bullet-style parameter list. It is front-loaded with the purpose and each sentence adds value. Minor improvement: could be slightly more concise by grouping related parameters, but it is well-structured.

  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 7 parameters and an output schema (not shown in detail), the description covers all inputs and the basic function. It does not describe the output structure, but the presence of an output schema mitigates that. Error cases or edge cases (e.g., invalid sort_by values) are not mentioned, but overall it is sufficient for a listing tool.

  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%, meaning the schema alone provides no semantics. The description explicitly explains all 7 parameters, including their defaults and meanings (e.g., keyword for partial matching, category filter, pagination). This fully compensates for the lack of schema descriptions.

  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 retrieves a list of nodes from the knowledge graph. The verb '조회' (retrieve) and resource '노드 목록' (node list) are specific. Sibling tools are all mutation tools (delete, update, merge, ingest), so the purpose is distinct and easily understood.

  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 parameter-level guidance (e.g., empty keyword returns all nodes) but does not explicitly state when to use this tool versus alternatives. No comparison or exclusion criteria are given for sibling tools, though their functions are obviously different.

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

• merge_nodesA
  4.3/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Discloses that node_b is soft-deleted after merge and that merged_summary, if empty, results in simple append. Provides key behavioral traits but omits permissions or reversibility.

  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 sentence overview plus a clean Args section. Every sentence is informative; no fluff.

  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?

  Covers all three parameters and key behavior. Output schema exists, so return values not needed. No mention of errors or prerequisites, but adequate for a merge tool.

  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?

  With 0% schema description coverage, the description fully explains each parameter: node_a is kept, node_b is absorbed and soft-deleted, merged_summary is optional with default empty meaning append. Adds significant meaning beyond schema.

  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?

  Clearly states it merges two nodes into one, keeping node_a and absorbing node_b. Verb 'merge' and resource 'nodes' are explicit. Differentiates from sibling tools like delete_node.

  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?

  Describes which node is kept and which is absorbed, but does not explicitly state when to use this tool versus alternatives like delete_node or update_node. Usage is implied, not directed.

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