Server Quality Checklist

Tool Scores

• call_runai_apiA
  4/5.0
  Behavior3/5

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

  Since no annotations are provided, the description must carry the behavioral disclosure burden. It adds useful context: 'Bearer 토큰 인증은 자동' (Bearer token authentication is automatic) and 'DELETE 등 위험 작업은 confirm_destructive: true 필요' (dangerous operations like DELETE require confirm_destructive: true). However, it does not disclose response format, error handling, or other side effects, which are relevant for a generic API caller.

  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 short sentences, front-loaded with purpose, followed by prerequisite and safety conditions. Every sentence earns its place, with no redundant or extraneous content.

  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 generic API wrapper, the description is largely complete: it directs users to look up the endpoint spec first, explains authentication, and covers destructive safeguards. The only notable omission is explicit mention of the response format, but that is endpoint-dependent and accessible via search_runai_api_spec, so the description adequately scopes the tool's behavior.

  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 baseline is 3. The description adds no substantial parameter semantics beyond what the schema already provides; it merely reiterates the confirm_destructive requirement for DELETE operations, which is already documented in the 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?

  The description clearly states 'Run:AI REST API를 호출합니다' (Calls the Run:AI REST API), specifying the verb and resource. It also differentiates from siblings by instructing to check the endpoint with search_runai_api_spec first, positioning this tool as the actual API caller.

  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?

  Provides clear usage guidance: 'search_runai_api_spec으로 엔드포인트를 먼저 확인하세요' (check the endpoint first with search_runai_api_spec). It also includes relevant conditions like automatic Bearer token authentication and the need for confirm_destructive for DELETE operations. However, it does not explicitly state when not to use alternatives like execute_runai_cli.

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

• resolve_runai_namesA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses supported types and batch resolution capability, but doesn't mention error behavior, case sensitivity, or whether it's a read-only operation. This is adequate but not rich.

  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 sentences, front-loaded with the core purpose. The second sentence efficiently lists supported types and batch capability. Zero 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?

  For a single-parameter tool with a well-documented schema, the description covers the main operation, supported types, and batch capability. Since there's no output schema, it doesn't detail return format, but the phrase 'ID로 변환' implies the output. It's nearly complete, though minimal.

  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 is fully self-descriptive (100% coverage) with the 'resolve' array and entity type enum. The description adds context that multiple entities can be resolved at once, but this is already implied by the array type. No additional parameter semantics 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?

  The description clearly states the tool converts Run:AI entity names to IDs, with a specific verb ('변환합니다') and resource ('Run:AI 엔티티 이름'). It also lists supported entity types, distinguishing it from the generic sibling tools like call_runai_api.

  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?

  It explains the context: 'API는 ID를 요구하지만 사용자는 이름만 아는 경우가 대부분입니다' (the API requires IDs but users usually only know names), implying when to use the tool. However, it doesn't explicitly name alternatives or exclusions, so it stops short of a 5.

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

• search_runai_api_specA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses meaningful behavior such as deprecated endpoints being hidden by default and alternative APIs being suggested. However, it does not explain search mechanics, result format, or potential edge cases (e.g., ambiguous queries or result limits), 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.

  Conciseness4/5

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

  The description is front-loaded with the core purpose, then follows a well-organized, pipe-delimited list of API categories. While long, the enumeration is directly relevant for a tool that searches a broad API surface, and it is structured for readability. It is not excessively verbose for its purpose.

  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 complexity of Run:AI's API landscape and the absence of an output schema, the description provides a thorough overview of what the tool can find, including many categories and the deprecated-endpoint behavior. It does not specify return formatting or detailed search options, but it is sufficient for an agent to understand the tool's capabilities and likely output.

  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 baseline is 3. The description adds value by explaining the scope of what can be queried via the 'query' parameter and by explicitly relating the 'include_deprecated' parameter to the default behavior of hiding deprecated endpoints and suggesting alternatives. This goes beyond the simple 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 uses a specific verb ('검색하여 찾습니다') and resource ('OpenAPI 스펙'), and clearly states it finds API endpoints, HTTP methods, and request schemas for a given task. It also distinguishes itself from siblings that execute API calls or resolve names by emphasizing it is a search/spec-lookup tool.

  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: it is used to locate the necessary API information before making calls, and it outlines the full scope of what can be searched. It does not explicitly mention when not to use it or name alternatives, but the intent is clear and there are no misleading exclusions.

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

• execute_runai_cliA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden for behavioral disclosure. It adds useful context like local session, port-forward tunneling, streaming logs, and --follow, but omits safety considerations, permissions, return value format, and error behavior for an execution tool that can run arbitrary commands inside containers.

  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 focused sentences: purpose comes first, followed by supported subcommands and an explicit pointer to sibling tools for other operations. No filler 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 is strong on purpose and usage, but the tool is a CLI execution tool with no output schema, and the description does not mention return output, error handling, or exit behavior. That gap matters for invocation correctness. However, the supported-command scoping and API alternative guidance make it minimally viable.

  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 covers 100% of parameters, so baseline is 3. The description adds value by narrowing command_args to the allowed subcommands and giving concrete examples (nvidia-smi, bash, --follow). timeout_seconds is clarified in the schema with 'Use 0 for port-forward', but the description itself doesn't add timeout guidance beyond the 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?

  Description clearly states it executes Run:AI CLI local session operations and enumerates specific subcommands (port-forward, exec, attach, logs, diagnostics). It also explicitly distinguishes from siblings like search_runai_api_spec and call_runai_api by limiting scope to API-irreplaceable tasks.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides explicit guidance: 'API 대체 불가능한 작업만' (only tasks that cannot be replaced by API) and lists exactly when to use each subcommand. It also says to use search_runai_api_spec + call_runai_api for workload create/delete/query, naming alternatives clearly.

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