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

With no annotations, the description carries the full burden. It discloses that it 'Returns paths to separated stem files' and provides a default output_dir, implying disk writes. However, it doesn't explicitly state whether the input is modified, whether files are overwritten, or performance requirements. It gives useful context but isn't exhaustive.

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 long but every part is necessary—the model list is essential because the schema lacks enums. It front-loads the purpose, then details models, parameters, and an example, with no filler.

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 the presence of an output schema and detailed parameter descriptions, the tool is well-covered. The description includes all three parameters, model options, defaults, and an example. It could mention input file format support or overwriting behavior, but it's largely complete.

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%, and the description compensates fully: it explains input_file, model with a complete list of valid values and their tradeoffs, and output_dir with default. The example clarifies the return structure.

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 clearly states 'Separate audio into stems using SOTA AI models' with a specific verb (separate) and resource (audio into stems), and lists named models. However, it doesn't explicitly differentiate from sibling tools like 'split_stems' or 'export_stems', so it misses explicit sibling differentiation.

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 provides model selection guidance (e.g., 'bs6' for fast, 'polarformer' for best vocals) and says it's 'much better than Demucs alone', but doesn't explicitly state when to use this tool instead of alternatives like split_stems or export_stems. No exclusions or alternative tool references.

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