Server Quality Checklist

Tool Scores

• gauge_lintA
  3.7/5.0
  Behavior3/5

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

  Without annotations, the description discloses that the tool runs without LLM calls, is fast, and returns structured JSON. However, it does not state whether it modifies anything, requires a connection, or how it accesses the target server's descriptions.

  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, each earning its place: the first defines the primary purpose and output, the second adds performance characteristics. No redundancy or filler.

  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?

  Given the lack of an output schema and five optional parameters, the description explains the output format at a high level but omits details on connection prerequisites, specific lint rules, and the exact JSON structure. This leaves some ambiguity for the agent.

  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 already provides 100% coverage with descriptions for all five parameters, so the description does not need to add parameter details. It adds no parameter-related meaning beyond the schema, aligning with the baseline of 3.

  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 a specific action: linting the tool description text of the target MCP server and returning improvement points as structured JSON. This distinctly separates it from sibling tools like gauge_connect or gauge_report.

  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 linting tool descriptions but provides no explicit guidance on when to choose this tool over alternatives, no exclusions, and no mention of prerequisites such as an existing server connection.

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

• gauge_reportA
  3.8/5.0
  Behavior3/5

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

  No annotations are present, so the description must convey behavior. It discloses that the tool returns average metrics and improvement recommendations, but it does not clarify whether it modifies any state or its safety profile. This is minimal but not misleading.

  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 sentences, front-loaded with the primary action, and every sentence adds value (purpose and output). No filler or redundancy.

  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 one-parameter tool with no output schema, the description provides a high-level explanation of the output ('平均メトリクスと改善推奨事項'). It is sufficient for a basic understanding, though it could elaborate on the exact nature of the metrics or error handling.

  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 covers 100% of the parameter (trace_ids) with a description indicating the list of trace IDs. The tool description does not add extra semantic detail about the parameter beyond what the schema states, so it scores 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 clearly states a specific verb ('生成する' - generates) and resource ('統合レポート' - integrated report) from multiple trace sessions, distinguishing it from siblings like gauge_compare or gauge_evaluate by focusing on aggregation and recommendations.

  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 generating a combined report from trace sessions but does not explicitly state when to use it over alternatives or when not to use it. No exclusion criteria or sibling comparisons are provided.

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

• gauge_disconnectA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It clearly states the action (disconnect), the consequence (end trace session), and the return value (trace summary metrics). This goes beyond a mere verb-phrase restatement, though it does not mention edge cases like invalid session IDs or whether the action is irreversible.

  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 concise sentence that front-loads the primary action, followed by the key return behavior. There is no wasted wording or unnecessary repetition of schema details.

  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 relatively simple tool with fully described parameters, the description is appropriately complete: it states the connection-teardown action, session termination, and return value. The lack of an output schema is partially compensated by the explicit mention of a trace summary, though more detail about return structure or failure behavior would push it to a 5.

  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 already fully describes both parameters (session_id and task_success), and schema description coverage is 100%. The tool description does not add any additional parameter-level semantics, 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 uses a specific verb ('切断', disconnect) and resource ('対象MCPサーバー', target MCP server) and clarifies it ends the trace session and returns a trace summary. This clearly distinguishes it from sibling tools like gauge_connect (which establishes a connection) and gauge_report (which likely reports data).

  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 after a connection has been established (via gauge_connect) by mentioning disconnection and trace session termination, but it does not explicitly state when to use it versus alternatives or provide any when-not-to-use guidance. The context is clear but the usage guidance is only implied.

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

• gauge_evaluateA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description is the sole source of behavioral info. It states it returns pass/fail and detailed evaluation, and implies a read-only analysis, but does not explicitly confirm whether it has side effects or requires specific permissions. This is adequate but not comprehensive.

  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, focused sentence that front-loads the primary action and includes the key prerequisite (gauge_disconnect). It is concise with no unnecessary 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?

  The description covers the tool's main purpose, the prerequisite, and the return type (pass/fail and detailed evaluation). Since there is no output schema, this return info is valuable. It does not go into edge cases or detailed output structure, but it is sufficient for common usage.

  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 has full coverage of parameters with descriptions, so the baseline is 3. The description adds no additional parameter semantics beyond mentioning success criteria and trace data, which is already 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 the tool evaluates trace session results based on success criteria, using the verb '評価する' and specifying the resource (trace data from sessions ended with gauge_disconnect). It distinguishes from siblings by referencing gauge_disconnect and focusing on post-session evaluation.

  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 indicates this tool is intended for evaluating sessions that have been ended via gauge_disconnect, providing a clear context. It does not explicitly mention alternative tools or exclusion cases, so it lacks full when-to-use contrast.

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

• gauge_proxy_callA
  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 full burden. It does disclose useful behavioral traits: the call is automatically recorded as a trace, and the result includes the target tool's response and call metrics. However, it does not mention potential side effects on the target server or any permission requirements, which remains a gap for a proxy that could invoke arbitrary tools.

  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, compact sentence in Japanese that front-loads the main purpose, then adds trace recording and result content. No unnecessary words or repetition; every clause earns its place.

  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 proxy tool with no output schema, the description explains the return value structure (target response and metrics) and the automatic trace recording. It gives enough context to use the tool safely, though it could mention that the target tool's effects depend on the specific tool invoked, but this is not a critical omission.

  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 covers 100% of parameters with descriptions, so the baseline is 3. The tool description adds no extra semantic meaning beyond the schema; it only repeats that the call goes through gauge_connect, which is already in the session_id parameter description.

  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 specific action (calls a target MCP server's tool) and the resource (through a gauge_connect session). It inherently distinguishes from siblings by being the only tool that proxies tool calls, while others manage connections or perform lint/compare/evaluate/report functions.

  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 phrase 'gauge_connectで確立した接続を通じて' provides clear context that this tool is to be used after establishing a connection with gauge_connect. However, it does not explicitly state when NOT to use it or name alternative tools, leaving room for more direct comparative guidance.

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

• gauge_compareA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses the return value structure (overall_verdict and per-metric comparison results), which is useful behavioral information. However, it does not mention any side effects, prerequisites, or error conditions, though for a comparison tool these may be less relevant.

  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, concise sentence that states the core action and return value without redundancy. It earns its place with no filler.

  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?

  Given the tool's simplicity and the absence of an output schema, the description provides the essential purpose and return value information. However, it lacks any mention of prerequisites (e.g., traces must exist) or potential error conditions, leaving it slightly incomplete for agents that need to anticipate failures.

  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 full Japanese descriptions for both required parameters, covering 100% of the parameters. The description adds no extra parametric meaning beyond restating the comparison context, so it doesn't improve on 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 that the tool compares a baseline trace with a new execution trace to determine metric improvement/deterioration, and specifies the return value includes overall_verdict and per-metric results. This distinguishes it from sibling tools like gauge_lint or gauge_report, which serve different purposes.

  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 does not explicitly mention alternative tools or exclude use cases, but the comparison purpose is clear from the tool name and description. It provides context that this is for comparing traces after changes, which is implied by the parameter names and descriptions.

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

• gauge_connectA
  4.2/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the full burden. It explains the behavior of connecting, starting a trace session, returning session_id and tool list, and directing the caller to proxy calls. This gives a clear behavioral contract beyond 'connect' and is appropriate for a connection tool, though it does not cover edge cases like reconnection or cleanup.

  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 sentences long, front-loaded with the verb and action, and every sentence earns its place: it states what it does, what it returns, and the next step. No redundant or vague phrasing exists, making it concise and 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?

  With six optional parameters and no output schema, the description appropriately explains the return value (session_id and tool list) and the intended follow-up action. It is complete enough for a connection tool, though it could mention behavioral nuances like whether repeated connects are allowed or the session lifecycle. The cross-reference to gauge_proxy_call adds valuable context.

  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 complete descriptions for all six parameters (100% coverage), so the baseline is 3. The tool description itself does not add parameter-specific semantics beyond what the schema already states, which is acceptable given the schema's thoroughness. No additional clarification is needed.

  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 connects to a target MCP server and starts a trace session, and it names the specific return values (session_id and available tools list). This distinguishes it from sibling tools like gauge_proxy_call (which invokes tools) and gauge_disconnect (which ends sessions). The verb+resource combination is specific and unambiguous.

  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: use this to establish a session and then instructs the caller to use gauge_proxy_call for subsequent tool calls, naming the alternative. It does not explicitly state when not to use it (e.g., if already connected), but the session-starting role is self-evident and the pointer to gauge_proxy_call gives practical guidance.

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