search_song

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.

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.

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.

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.

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.

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.