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

No annotations are provided, so the description carries the full burden and does so thoroughly: it discloses the hard English-only constraint for keywords/composer, how negation is mapped and relaxed, the half-time BPM trap that silently drops valid tracks, LLM daily quota degradation (llmQuotaExceeded), and translation_failed semantics. It also flags that returned track_url is audition-only.

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 a one-line bilingual summary before diving into searchField, negation, fields, and BPM caveats, and sectioned with headers. It is dense and long, with bilingual restatement adding some redundancy, but for a 29-parameter tool most content 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?

Despite no annotations and no output schema, the description covers the return shape ({ total, appliedSearchField, searchId, fields, tracks[], search_url }), conditional keys (expanded, derivedNegations), and error flags. Combined with the schema, an agent has everything needed to invoke and interpret results correctly.

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 high (90%), but the description still adds substantial meaning: it explains that include facet values within a dimension are AND (except includeLabels/includeAlbums which are OR) while exclude* excludes on any match, that bpmMin/bpmMax and durationMin/durationMax must be paired, and that partition omission merges the two site partitions. It also documents pageSize clamping tied to the fields choice.

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 and resource ('检索曲目或专辑' / searches the Kindle Music production-music catalog) plus the dimensions it filters on (keyword, facet, BPM, duration). It also names sibling tools by role (km_resolve for filenames/links, km_vocabulary for facet values), so an agent can distinguish it without opening schemas.

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?

Gives explicit when-to-use guidance across all seven searchField modes (keyword vs ai vs semantic vs track vs album vs lyrics vs composer), including the fallback chain (semantic degrades to ai). It states prerequisites ('include*/exclude* 的取值必须先用 km_vocabulary 取') and the routing rule '先用 km_resolve 定位' for downloaded filenames/links/IDs.

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