Server Quality Checklist

Tool Scores

• get_player_recordsC
  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. It mentions the tool returns recent game details in a list format, but doesn't describe important behavioral aspects like whether this is a read-only operation, potential rate limits, authentication requirements, error conditions, or what 'recent' means temporally.

  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 with just two sentences that directly state the tool's purpose and return format. Every word serves a purpose with zero waste or redundancy, making it easy to parse and understand quickly.

  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 with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain the return format beyond 'list of recent game details,' doesn't mention behavioral constraints, and provides no usage context. The description should do more to compensate for the lack of structured metadata.

  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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any meaningful parameter semantics beyond what's in the schema - it doesn't explain parameter relationships, usage patterns, or provide examples that go beyond the schema documentation.

  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's purpose: '获取玩家的历史对局记录' (get player's historical game records) and specifies the return format '返回最近的对局详情列表' (returns a list of recent game details). It uses a specific verb+resource combination but doesn't explicitly differentiate from siblings like get_player_stats.

  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 no guidance on when to use this tool versus alternatives. It doesn't mention when this tool is appropriate compared to siblings like get_player_stats or get_leaderboard, nor does it specify any prerequisites or exclusions for usage.

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

• get_player_statsC
  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. While it indicates this is a read operation (获取/获取 means 'get'), it doesn't address important behavioral aspects like whether this requires authentication, what happens if the player doesn't exist, whether there are rate limits, or how fresh the statistics are. The description is minimal and doesn't provide sufficient behavioral context for a tool with no annotation coverage.

  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 appropriately concise with two sentences that efficiently communicate the core functionality. The first sentence states the purpose, and the second specifies what data is returned. There's no wasted language or unnecessary elaboration. However, it could be slightly more structured by explicitly separating purpose from return values.

  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 read-only statistics tool with no annotations and no output schema, the description provides basic but incomplete context. It tells what the tool does and what data it returns, but doesn't address important contextual elements like error conditions, data freshness, authentication requirements, or how the statistics are calculated. The absence of an output schema means the description should ideally provide more detail about return values, but it only lists them without explaining format or units.

  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 has 100% description coverage, with both parameters clearly documented in the schema itself. The description doesn't add any parameter information beyond what's already in the schema - it doesn't explain the format of mac_addr, clarify what constitutes a valid game_id, or provide examples. With complete schema coverage, the baseline score of 3 is appropriate as the description doesn't enhance parameter understanding.

  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's purpose: '获取玩家的战绩统计' (get player performance statistics) and specifies the types of data returned (win rate, total matches, net chips won). It distinguishes itself from siblings like 'get_game_state' or 'get_leaderboard' by focusing on individual player statistics rather than game state or rankings. However, it doesn't explicitly contrast with 'get_player_records' which might be a closer sibling.

  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 no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over 'get_player_records' (which might provide detailed records rather than aggregated statistics) or 'get_leaderboard' (which might show comparative rankings). There's no discussion of prerequisites, timing considerations, or exclusion criteria.

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

• get_leaderboardB
  3.3/5.0
  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 mentions sorting and limiting results, but lacks details on permissions required, rate limits, error handling, pagination, or what the output format looks like (e.g., list of players with scores). For a read operation with no annotation coverage, this is a significant gap in transparency.

  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, efficient sentence in Chinese that directly states the tool's function and key features (sorting criteria). It is front-loaded with the main purpose and includes no unnecessary details, making it highly concise and well-structured.

  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 moderate complexity (3 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose and sorting options but lacks output details, error handling, and behavioral context. With no output schema, the description should ideally hint at return values, but it doesn't, leaving gaps in completeness for effective agent use.

  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 the schema already documents all parameters (game_id, sort_by, limit) with descriptions and defaults. The description adds context by listing the sorting options (wins, win_rate, net_chips), which aligns with the schema but doesn't provide additional semantic meaning beyond what's in the schema. Baseline 3 is appropriate when the schema handles parameter documentation effectively.

  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's purpose: '获取游戏排行榜' (get game leaderboard) with specific sorting criteria (wins, win rate, net chips). It distinguishes itself from siblings like get_player_stats or get_player_records by focusing on ranking across players rather than individual data. However, it doesn't explicitly differentiate from list_games, which might also involve listing but not ranking.

  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 when a ranked list of players is needed for a specific game, based on sorting criteria. It doesn't provide explicit guidance on when to use this tool versus alternatives like get_player_stats (for individual stats) or list_games (for game listings), nor does it mention prerequisites or exclusions, leaving some ambiguity.

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

• list_gamesB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but only states what the tool does, not behavioral traits. It doesn't disclose whether this is a read-only operation, if it requires authentication, rate limits, or what format the list returns. For a tool with zero annotation coverage, this is insufficient.

  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, efficient sentence in Chinese that directly states the tool's purpose with no wasted words. It's appropriately sized and front-loaded with the core functionality.

  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 (0 parameters, no output schema), the description is minimally adequate but lacks behavioral context. Without annotations or output schema, the description should ideally mention what the return value looks like (e.g., list format, game identifiers) to be more complete.

  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 tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the lack of inputs. The description doesn't need to add parameter information, and the baseline for 0 parameters is 4.

  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 action ('获取' - get/retrieve) and the resource ('当前大厅可用的游戏列表' - list of available games in the current lobby). It distinguishes from siblings like get_game_state (specific game state) or join_game (joining action). However, it doesn't specify what 'available' means in detail.

  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 when needing to see what games are available in the lobby, which differentiates it from siblings that operate on specific games or player data. However, it doesn't explicitly state when NOT to use it or name alternatives like get_leaderboard for ranking information.

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

• submit_actionB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It reveals important behavioral traits: this is a long-polling interface that blocks/wait after execution, which is crucial information not inferable from the schema alone. However, it doesn't disclose other important aspects like error conditions, timeout behavior, authentication requirements, or what happens when the game ends versus when it's the player's next turn.

  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 appropriately concise with just two sentences that both earn their place. The first sentence states the core purpose, and the second sentence adds crucial behavioral information about the long-polling nature. No wasted words or redundant information. Could potentially be improved with slightly more structured formatting.

  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 3-parameter tool with no annotations and no output schema, the description provides adequate but incomplete coverage. It explains the long-polling behavior which is important context, but doesn't describe what the tool returns (though no output schema exists), error conditions, or how the action_data should be structured beyond being JSON. Given the mutation nature of 'submit' and lack of annotations, more behavioral disclosure would be beneficial.

  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 the schema already documents all three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions '动作数据JSON字符串' (action data JSON string) which aligns with the schema's action_data description but doesn't provide additional semantic context. Baseline score of 3 is appropriate when 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 clearly states the tool's purpose as '提交博弈决策' (submit game decision/action), which is a specific verb+resource combination. It distinguishes itself from sibling tools like get_game_state or join_game by focusing on action submission rather than retrieval or joining. However, it doesn't explicitly differentiate from potential similar action tools that might exist in other contexts.

  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 implied usage context by mentioning it's a '长轮询接口' (long-polling interface) that waits for the next turn or game end after execution. This suggests when to use it (during active gameplay turns) but doesn't explicitly state when NOT to use it or provide clear alternatives among the sibling tools. No prerequisites or comparison to other action-related tools are mentioned.

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

• get_game_stateA
  3.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it's a long-polling interface that blocks until specific conditions (player's turn or game end). This reveals important performance characteristics not evident from the input schema alone.

  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 perfectly concise with two sentences that each earn their place: the first states the purpose, the second explains the blocking behavior. No wasted words, well-structured and front-loaded.

  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 tool with no annotations and no output schema, the description provides adequate but incomplete context. It explains the blocking behavior well but doesn't describe what the game state response contains, error conditions, or how to interpret the 'game end' condition.

  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 description coverage is 100%, so the schema already documents both parameters (room_id and mac_addr). The description doesn't add any parameter-specific information beyond what the schema provides, maintaining the baseline score for high schema coverage.

  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's purpose: '获取当前游戏状态' (get current game state). It uses a specific verb ('获取') and resource ('游戏状态'), but doesn't distinguish it from sibling tools like 'get_player_stats' or 'get_player_records' that might also retrieve game-related information.

  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 by explaining it's a long-polling interface that blocks until the player's turn or game end. However, it doesn't explicitly state when to use this versus alternatives like 'list_games' or 'join_game', nor does it mention prerequisites or exclusions.

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

• join_gameA
  4.4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and does an excellent job. It discloses critical behavioral traits: this is a long-polling interface that blocks until match success and player's turn, or times out. This reveals important blocking behavior and timeout characteristics not evident from the schema alone.

  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 perfectly concise - two sentences that efficiently convey the core purpose and critical behavioral characteristics. Every word earns its place with no wasted text, and the information is front-loaded appropriately.

  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 tool with no annotations and no output schema, the description provides strong context about the blocking/long-polling behavior. It could be more complete by mentioning what happens after successful match (e.g., returns match details, triggers next step) or typical timeout duration, but covers the essential operational characteristics well.

  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 the schema already documents both parameters completely. The description doesn't add any additional parameter meaning beyond what the schema provides, maintaining the baseline score of 3 for high schema coverage situations.

  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 ('加入游戏匹配队列' - join game matchmaking queue) and resource (game matching system). It distinguishes from siblings like get_game_state or submit_action by focusing on queue entry rather than game state retrieval or action submission.

  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 about when to use this tool - when a player wants to join a matchmaking queue. It doesn't explicitly mention when NOT to use it or name specific alternatives, but the behavioral description implies this is for queue entry rather than other game operations.

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