get_lyrics

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

With no annotations provided, the description carries full behavioral disclosure burden. It discloses the tool WRITES a .lrc file (a side effect beyond simply retrieving), explains the file location logic (audio_dir provided vs MUSIC_MCP_LYRICS_DIR config fallback). Notably the description reveals this is not purely a read operation—it persists to disk—which is valuable behavioral transparency absent from any annotations.

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?

Two crisp sentences, zero filler. Every clause adds value: LRC preference, identification options, and write-location logic. Highly efficient and front-loaded with the core purpose.

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 mutates the filesystem (writes .lrc), has 5 parameters all undocumented in schema, and no annotations—yet the description conveys the essential write behavior, identification options, and output-location logic. It covers the core complexity well; minor gaps include what duration_ms affects (LRC timing?) and return value behavior, though an output schema exists to cover return structure.

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 bears full responsibility. It explains the meaning of norm_key and title+artist (identification methods) and audio_dir (output location), which covers 3 of 5 parameters. However, duration_ms and the precedence of norm_key vs title+artist semantics are not clarified beyond what the schema shows.

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 clearly states the verb (获取/retrieve lyrics), the resource (lyrics for a song), and a specific preference (LRC format prioritized). It distinguishes from siblings—search_songs is for searching not retrieving lyrics, download_song downloads audio not lyrics. The purpose is specific and action-oriented.

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?

It explains the two ways to identify a song ('传 norm_key 或 title+artist'), giving usage direction. However, it doesn't mention when to choose this vs siblings or any exclusions/alternatives, so the when-to-use guidance is implied rather than explicit.

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