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

Annotations already declare this as a non-read-only, non-idempotent, open-world write, and the description adds meaningful behavior beyond them: the video_url is returned synchronously in the same call, and unsupported model versions fail with a 400 rather than silently degrading. It does not explain that repeated calls create distinct videos, which matters given idempotentHint=false.

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?

Three tight sentences, front-loaded with the effect and return value, followed by eligibility and the endpoint. The trailing 'POST /music/video-generate' is the least useful element for an agent but costs almost nothing.

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 correctly fills that gap by naming the returned video_url and confirming synchronous return. Combined with the model-version failure rule, an agent has what it needs to invoke correctly, with only minor gaps around retry/idempotency behavior.

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?

There is only one parameter (song_id) and the schema covers it at 100% with its format and account-scoping note, so the schema carries the semantic load. The description adds no extra parameter meaning beyond what the schema states, making the baseline 3 appropriate.

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 artifact: 'Make a lyrics video (mp4) for one song and return its video_url'. The resource (video output for an existing song) is clearly distinguished from siblings like mureka_create_song, mureka_create_instrumental, and mureka_extract_stems.

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?

Gives a concrete eligibility rule: works for songs on V9, V8, O2, V7.6, V7.5-all and edited songs, while a V9.5 song returns 400. That is real when-it-works/when-it-fails guidance, though it never names an alternative tool or workflow for handling the unsupported case.

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