daily_recommendations

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

With no annotations, the description carries the burden and does so reasonably: it discloses the per-platform source composition (QQ radar + guess-you-like + recommended playlists; Netease daily + playlists; Kugou daily) and a genuine operational nuance — Kugou works without login, implying QQ/Netease do not. It does not state failure behavior when unauthenticated for QQ/Netease or whether results are cached/paginated.

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?

Front-loaded with the core purpose, then compact per-platform breakdown, then return shape. Dense but nearly every token carries information; only the semicolon-separated platform list is slightly dense to parse on a first read.

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 single optional-parameter read tool with an output schema, this covers purpose, per-platform sourcing, auth nuance, and the response shape. The remaining gap is guidance on auth failure paths and whether to call a credential sibling first, which matters given the stated login dependency for QQ/Netease.

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 coverage is reported as 0%, so the description must supply parameter meaning; it does repeat the three service values and, more usefully, explains what content each platform returns, which is real added meaning beyond the enum. However it never mentions the default (qq_music) or what happens if service is omitted, leaving that to the schema's $defs.

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?

Names the resource precisely (today's platform recommendations) and adds a distinguishing gloss — 'the raw material for a daily playlist' — which separates it from the sibling create_daily_playlist. An agent can tell it is a read of upstream recommendation feeds rather than a playlist write, though it never names the sibling explicitly.

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?

Usage is implied through the 'raw material for a daily playlist' framing, suggesting it is called before playlist creation, and the per-platform source list hints at what each choice yields. There is no explicit when-to-use/when-not-to-use statement or prerequisite call chain (e.g. it does not say to call credential_status first for QQ/Netease).

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