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

Adds real context beyond the annotations: the job is free and the result lands in the person's library, and it flags the approval-gated path. Annotations already cover safety and idempotency hints, so the remaining gap is minor (no mention of async/job completion behavior).

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?

Four compact sentences, front-loaded with what the tool produces, then the choice, then cost/output, then the prerequisite. Slightly dense with semicolon-joined clauses but no wasted sentences.

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?

Covers the things an agent would otherwise guess wrong: cost, where output goes, and the source-audio prerequisite. With no output schema, it could still say more about the return value (a job handle to poll via get_job), which is the main omission.

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; the description still adds meaning by framing the cut choice as short-form vs whole song and by explaining that track_id must come from a song made here unless the audio is first edited via edit_song. It doesn't elaborate on idempotency_key or approval_id beyond what the schema already says.

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 ('turn a song with lyrics into a lyric video') and immediately characterizes the output (words timed to vocals over animated visuals). This clearly separates it from siblings like make_music_video or create_video without opening their 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?

Explicitly routes the agent: use hook vs full, and use edit_song first when the audio is the person's own rather than a song made here. It doesn't name the nearest sibling (make_music_video) as an alternative for comparison, which keeps it below a 5.

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