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

With no annotations, the description carries the full burden and does well: it discloses the failure mode (resolved=null when unrecognized or absent from library), the kind/source taxonomy, and gaps in the toolchain (playlists have no MCP reader; video-site links usually cannot yield a track name, so use km_similar_by_audio). It does not mention latency, network calls, or explicit read-only status, so it stops short of a 5.

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?

Bilingual and long, but structured with headers (When/Returns) and a per-kind bullet list, with purpose and the km_search caveat front-loaded. The kind-by-kind routing is dense but each branch earns its place; only minor redundancy comes from the paired Chinese/English text.

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?

No output schema exists, so the description must explain returns and it does: it documents the { q, resolved } envelope plus the fields returned per kind/source and the exact next call for each. Nothing an agent needs to act on the result is missing.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema field by enumerating accepted input forms (album/label/pick-list/playlist/search-page URLs, external links, hyphenated codes) and stressing the 'exactly as the user gave it' constraint implicitly.

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+resource pair (resolve a filename/link/album code into an actionable object) and explicitly differentiates from the sibling km_search ('不要把它们当关键词丢进 km_search'). An agent can identify the tool's job without opening the schema.

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?

Provides explicit when-to-use triggers (pasted filename, UPM/kindlemusic link, hyphenated code) and the negative case (do not treat as keyword in km_search, which yields zero results). It also routes to the correct follow-up tool per kind (km_track_versions, km_get_result_set, km_similar_by_track), so alternatives are named and conditioned.

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