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

Annotations only flag it as a non-read-only, non-destructive write. The description adds the cost (15 credits), the refund-on-failure policy, the asynchronous latency (~30 seconds), and the required post-call polling of get_song. That is exactly the operational context an agent needs beyond the annotation set.

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 dense sentences with no filler: precondition, effect and cost, then the required follow-up. The precondition and the follow-up action are both front-loaded where an agent will read them.

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 correctly explains that results arrive indirectly via polling get_song, and covers cost, failure handling, and timing. It stops short of saying where the shot plan surfaces in the get_song response, which would fully close the loop.

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% for the single song_id parameter, so the schema documents nothing about format or source. The description implies the song must already carry a mode 'dna' analysis but never states how to obtain or format the song_id, leaving most parameter meaning to inference. Adequate but thin.

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: it 'builds its story and beat-synced shot plan (scenes with seconds and image/video prompts) from the existing analysis.' The precondition 'For a finished song analysed with mode dna' makes it distinguishable from sibling analyze_song, so an agent can route without opening the schema.

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 an explicit precondition (finished song already analysed with mode 'dna') and a follow-up step ('Then poll get_song'), naming the sibling to use next. It does not state the negative case — e.g. run analyze_song first if no analysis exists — so it falls just short of full when/when-not guidance.

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