liked_songs

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

With no annotations at all, the description carries the full disclosure burden, and it does well: it reveals a side effect beyond a read, namely that the snapshot is written to state/<platform>_liked.json using the same format as the playlist-creation flow. It also warns about truncation for large accounts and surfaces need_login/diagnostics in the response shape. What it lacks is an explicit statement that authentication is a prerequisite, which the agent must infer from need_login.

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?

The purpose and parameter rules come first, which is good, but the block that spells out the full return JSON, field by field, duplicates what the output schema already declares and adds length without adding meaning. The most valuable sentence, about writing the snapshot file, is buried at the end and easy to skim past. The definition could cut the response-shape dump and keep only the side-effect note.

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?

The tool is simple: two optional parameters and an output schema that already defines the response, so the description does not need to explain return values. It nonetheless covers the two genuinely non-obvious behaviors, truncation and the state-file side effect, along with the login flag. The only real gap is guidance distinguishing this tool from the platform-specific liked-songs sibling.

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 0%, so the description must fill the gap, and it does: it enumerates the three valid service values and, more importantly, explains that limit=0 means all songs whereas limit>0 truncates to the first N, a semantic the bare default of 0 does not convey. The parameter meaning goes materially beyond the schema, though platform-specific behavioral differences beyond truncation are not detailed.

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 action on a specific resource: fetch the full set of liked/favorited songs on one platform, with the clarifying aside '全量，不是摘要' that separates it from an analytics tool. The purpose is clear, and it distinguishes its output from a statistical summary. However, it never mentions the near-identical sibling ncm_liked_songs, so an agent can't tell the two apart from the description alone.

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 gives a concrete usage rule: pass limit=0 for everything, or a value above 0 to truncate large accounts such as QQ accounts with 700+ songs. What's missing is guidance on when to pick this tool over ncm_liked_songs, recent_tracks, or my_playlists; it never names when not to use it. The intended usage is implied, not stated explicitly against alternatives.

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