separate_audio_stems

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions return values (task id, status, URL) but omits critical behavioral aspects such as that this is a long-running asynchronous task, that the 'wait' parameter controls polling, or that it creates a new resource (a mutation). No safety profile, permission requirements, or side effects are disclosed, leaving significant gaps.

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?

The description is a single sentence with no filler. It efficiently conveys the core purpose and expected output structure, achieving maximum conciseness without sacrificing essential 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?

The tool has 8 parameters including complex enums (stem_name has ~100 options), yet the description provides no context on how separation modes work, when to use 'wait' vs 'callback_url', or how output URLs are delivered. With no output schema and no annotations, the description is insufficient for an agent to confidently invoke this tool without external knowledge.

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 75% because most parameters (type, wait, stem_name, callback_url, timeout_ms, poll_interval_ms) have their own descriptions in the schema. The tool description adds nothing about parameters beyond the schema, so it does not compensate for the 25% uncovered (task_id and audio_id are minimally described but are required and self-explanatory). Baseline of 3 is appropriate since the schema handles most semantics.

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 states 'Create a Suno task on RunAPI (separate audio stems)' which clearly identifies the verb (create), resource (Suno task on RunAPI), and function (separate audio stems). It unambiguously indicates what the tool does and distinguishes it from sibling tools that handle generation, lyrics, or mixing. However, it does not explicitly compare with other 'create task' possibilities, so it misses the top score.

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?

The description gives no guidance on when to use this tool versus alternatives. It does not mention circumstances where separation is appropriate, nor does it explain prerequisites like needing an existing task_id or audio_id. Without any usage context or exclusionary notes, the agent is left to infer from the tool name alone.

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