get_liked_songsRetrieve a user's liked songs from NetEase Cloud Music, defaulting to the current logged-in user. Returns recently liked songs first with liked dates and supports limit/offset pagination.
获取用户“喜欢”的歌曲（默认当前登录用户），和 App 里“我喜欢的音乐”歌单顺序一致：最近喜欢的在前，附带喜欢的日期。
| Name | Required | Description | Default |
|---|---|---|---|
| uid | No | 用户 ID；不填则为当前登录用户 | |
| limit | No | 返回条数，默认 50，最多 500 | |
| offset | No | 分页偏移量，默认 0 |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuine value beyond that: the result is ordered identically to the app's '我喜欢的音乐' playlist (most recent first) and each item carries its liked date. Pagination/rate-limit behavior is still unstated, which holds it at 4.
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?
A single front-loaded sentence: scope first, then the ordering and date detail. Every clause (default user, ordering, liked date) earns its place. Efficient without padding.
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?
With 3 optional params at 100% schema coverage, readOnly annotations, and no output schema, the description covers what is needed: what is returned, its ordering, and an extra returned field (the liked date). Only pagination semantics and behavior at the limit boundary are left implicit.
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 uid, limit, and offset are already fully documented. The description only echoes the uid default ('当前登录用户'), adding no syntax or constraint information beyond the schema. Baseline 3 applies when the schema carries the parameter burden.
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?
States a specific verb (获取/get) and resource (用户"喜欢"的歌曲), which is distinct from the sibling like_song (the write side) and from get_listening_history. The output ordering ('recently liked first') further pins down what is returned. It does not explicitly name which sibling a caller should use instead, keeping it a step short of a 5.
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 '(默认当前登录用户)' note and the ordering hint give a sense of when this tool applies, but there is no explicit guidance like 'use like_song to add, get_listening_history for play history.' The usage context is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.