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

Despite annotations already marking this destructive and idempotent, the description adds substantial behavioral context: matching lyrics that don't align return 409 and leave the song unchanged, results are synchronous (analysis.lyrics) or async (202), and videos made afterward use the lyrics while existing videos are untouched. This is exactly the kind of beyond-schema disclosure the annotations cannot supply.

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?

Dense but well front-loaded: the core action comes first, then format, then validation and timing semantics. Some sentences are long, but each carries distinct information rather than restating the title or schema.

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?

There is no output schema, so the description must cover return behavior, and it does: synchronous analysis reporting (analysis.lyrics) versus asynchronous 202, plus the 409 failure mode. For a two-parameter destructive mutation, the coverage is complete.

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 baseline is 3, but the description adds real meaning beyond the schema: lyrics may be plain text with Suno-style [Verse]/[Chorus] tags and (x2) repeat marks, or the contents of an SRT, WebVTT, or LRC file, and timing always comes from the audio. This clarifies the accepted input format in ways the schema's maxLength/minLength cannot.

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 leads with a specific verb + resource: 'Give a song its own lyrics, or replace them,' which unambiguously identifies the action. It does not name the sibling it contrasts with, such as clear_song_lyrics, so an agent must infer the distinction, but the purpose itself is stated with precision.

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 description implies usage ('replace them', 'your text fixes misheard words') and specifies rejection conditions, but never states when to choose this tool over clear_song_lyrics or reanalyze_song. It is adequate but leaves routing to inference.

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