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

Annotations only say readOnly=false, destructive=false, openWorld=false, idempotent=false; the description carries far more — credits are charged at prismposter.com parity, each job yields two takes in about a minute, the approval_required gate blocks all execution until the person answers, output is auto-saved to the library, and disallowed content is refused before any charge. The stated idempotency_key behavior is consistent with idempotentHint=false, since a fresh call still charges.

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?

Front-loaded with the purpose and the vocal/instrumental branch, then moves through cost, approval gate and refusals in a logical order. Sentences are long and the downstream-capability list ("then remix, extend, split into stems...") is more promotional than operative, but nearly every clause carries decision-relevant information.

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?

Given 11 optional params, real credit charges and no output schema, the description covers cost, latency, the approval loop and content policy well, and hints at the return (two takes). It does not say how to retrieve results after the job starts — no mention of get_job or track/job identifiers — which is the main gap for a tool with no output schema.

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 100% and the schema already explains style, lyrics vs prompt, instrumental, approval_id, idempotency_key and the reference_audio/clips/images exclusivity rules in detail. The description restates the broad shape ("set style, tempo, instruments, title and target length up to six minutes") but adds no syntax or edge-case meaning beyond the schema, so baseline 3 applies.

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?

Opens with a specific verb+resource ("Make an original song") and immediately splits the two modes — vocal from supplied lyrics, or instrumental from a description — which is the exact distinction an agent needs. It also names the adjacent capabilities (remix, extend, stems, lyric/music video) so the agent knows where the boundary with edit_song, extend_video and make_music_video lies.

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 real routing context: quote_job prices first and is free, and approval_required is returned when the person must decide something before anything runs. It states what is refused up front (under-18, public figures). It stops short of explicitly contrasting create_song with edit_song or extend_video for iterating on an existing song, so it is strong but not complete.

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