Server Quality Checklist

Tool Scores

• list_sourcesA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It does convey that the operation is a read-only list and that health status will be included, which is useful behavioral context. However, it does not disclose any limitations, caching, network dependence, or response details, so it stays at a high level.

  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?

  A single concise sentence with no filler. The action and target are front-loaded and every word contributes to the meaning.

  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 tool is low-complexity (no params, no nested objects) and the description sufficiently communicates what will be returned: a list of available free music sources and their health status. Since there is no output schema, it does a reasonable job of setting expectations, although the exact result structure is left unspecified.

  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?

  There are zero parameters and the schema coverage is 100%, so there is nothing meaningful for the description to add. The schema already completely defines the input surface; the baseline of 4 is appropriate.

  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 states a clear verb ('list') and a specific resource (currently available free music sources) plus an additional distinguishing element (health status). It doesn't explicitly call out sibling tools, but the resource type make it obviously different from song search and playback tools.

  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 sibling tools such as search_song or play_song. The description simply states what it does without hinting at the intended workflow or exclusions, leaving the agent to infer use cases.

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

• get_play_urlA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full behavioral burden. It discloses the most important trait — no playback is triggered, only a URL is returned — which implies a side-effect-free read. However, it does not disclose failure behavior, URL expiration, or ambiguous-query handling, which are meaningful gaps for a network-backed resolver.

  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 dense sentences with zero filler: the first states the purpose, the second gives the usage condition and the behavioral contrast. Every clause earns its place, and the core fact is front-loaded.

  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 3-parameter tool with full schema coverage and no output schema, the description supplies the essential contract: what it resolves, when to call it, and what it returns (an address, not playback). It falls just short of describing the return format or how resolution differs when song_id is provided versus a text query.

  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. The cross-reference '参数与 play_song 相同' adds no new semantic detail beyond what the schema provides. Baseline 3 applies because the description neither needs to nor does compensate for any coverage gap.

  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 opens with a specific verb+resource: '解析歌曲的直链播放地址' (resolve a song's direct playback URL), which states exactly what the tool produces. It also distinguishes itself from siblings with '只返回地址不播放' (only returns the address, doesn't play), cleanly separating it from play_song even though both share the same parameter set.

  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 gives an explicit trigger condition: '当其他工具需要具体音频 URL 时使用' (use when other tools need a concrete audio URL). The contrast with play_song is implied via '参数与 play_song 相同，只返回地址不播放', but it stops short of naming explicit when-not-to-use scenarios or other alternatives among the siblings.

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

• play_songA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden and does it well: it discloses automatic search/URL resolution, precise playback via song_id, and the ResourceLink return format that must be paginated through resource://read_from_http. It does not cover failure or error behavior, but the core data flow and consumption behavior are transparent.

  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 compact and well-structured: purpose first, then trigger conditions, then call modes, then return/consumption details. Every sentence contributes useful information with no filler.

  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 no output schema and no annotations, the description compensates by explaining the return type (ResourceLink), how to consume it, and the two valid call paths. It is slightly incomplete regarding the required query/song_id condition and the boundary with get_play_url, but is otherwise adequate for correct invocation.

  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 meaningful cross-parameter context: query can contain singer + song name, and song_id + source form an exact-playback path after search_song. It stops short of explaining whether query and song_id are mutually exclusive or which combination is required.

  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 states a clear verb-resource pair ('播放歌曲') and gives the exact user phrasings that should trigger this tool. It also implies a relationship with search_song by accepting its song_id, but it does not explicitly distinguish itself from sibling tools like get_play_url or local_player_control.

  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 provides explicit when-to-use trigger phrases and two clear invocation modes: free-text query with auto-search, or exact song_id plus source after a prior search_song call. However, it does not state when to prefer get_play_url or local_player_control, nor does it clarify that at least one of query/song_id is effectively required.

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

• search_songA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full disclosure burden. It compensates well: it reveals the return payload shape (list with source, song name, artist, album, duration), which matters because there is no output schema, and the per-result 'source' field implies cross-source aggregation behavior. It does not address empty-result or failure behavior, but these are minor for a read-only search tool.

  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 compact sentences with zero filler. The core action and scope are front-loaded in the first sentence, and the second packs usage triggers plus supported query formats and return fields. 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 medium-complexity search tool with no output schema, the description covers the essentials: scope (free sources), query formats, explicit trigger conditions, and return fields. Minor gaps are the absence of no-result or error behavior and no hint that results feed into downstream sibling calls like play_song or get_play_url.

  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 query, limit, and source, including explicit examples ('青花瓷' or '周杰伦' or '周杰伦 青花瓷'). The description's claim about searching by song name, artist, or combined terms largely duplicates those examples, adding only marginal meaning beyond the schema 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 states a specific verb and resource: 'search songs in free music sources' (在免费音乐源中搜索歌曲), which clearly distinguishes it from siblings like play_song, get_play_url, and list_sources. The search-versus-playback versus source-listing boundary is immediately obvious.

  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 explicitly lists the triggering user intents ('when the user asks to find a song, request a song, search for songs, or asks whether a song exists'), giving agents a solid decision rule. However, it does not name sibling alternatives or state when not to use this tool, though the alternatives are different enough that exclusion is inferred rather than stated.

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

• local_player_controlA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It discloses that this mutates/controls the local player, only works when LOCAL_PLAYER is enabled, and is not for hardware playback. It does not describe what status returns or the full effect of stop, but the main behavioral conditions are clear.

  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 with no filler. The core purpose and prerequisite are front-loaded, and the sibling routing is handled in one clause. Every sentence 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 two-parameter enum-driven tool, the description covers purpose, prerequisite, and sibling distinction. The main gap is that the status action's behavior/return value is not described and there is no output schema to fill that gap, but this is unlikely to prevent correct invocation.

  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 action enum and conditional url requirement are already fully documented in the schema. The description adds no parameter-specific meaning beyond what the schema provides, so the baseline score of 3 applies.

  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?

  States a specific verb ('控制') and resource ('本机媒体播放器 mpv/vlc') and clearly distinguishes itself from sibling play_song by saying hardware playback uses that tool. An agent can readily tell which tool to use for local PC playback versus hardware playback.

  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?

  Gives explicit when-to-use context ('电脑端本地播放场景'), a prerequisite (LOCAL_PLAYER config must be enabled), and an explicit exclusion with the alternative tool (play_song for 小智硬件播放). This is strong, actionable routing guidance.

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