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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds payload content beyond the annotations, but does not disclose what happens if analysis is missing (the reanalyze_song sibling implies this state exists) or any latency/retry 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?

Two tight sentences with no waste: the payload enumeration comes first and the usage hint second. Nothing is padded, though the fragments are terse enough that a little more structure could help.

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?

With no output schema, the description carries the return-value burden and does list the analysis components, which is the key missing information. It stops short of describing the shape of those components or the empty/failed state, so a small gap remains for a data-rich read tool.

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?

One parameter with 100% schema description coverage, so the schema documents song_id fully and the description adds no format or sourcing detail. Baseline 3 applies when structured fields do the heavy lifting.

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 enumerates the exact payload (word-timed lyrics, tempo, beats, sections, hook), which makes it distinguishable from get_song (metadata) and get_video. The verb is only implied by the name rather than stated, but the resource contents are unambiguous.

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?

'Use the section times to choose a trim for a lyric video' gives a downstream use case and implicitly routes to create_lyric_video/quote_lyric_video, but it never states when this should be called versus get_song or reanalyze_song, nor any prerequisite such as the analysis already existing.

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