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

Annotations only carry the generic mutation profile, and the description goes well beyond them: it explains the download_url requirement, the R2 staging of the input during the job, headless-browser processing, that result links expire after 1 hour, and that the uploaded input is deleted when the job ends. Retention and expiry behavior are exactly the kind of traits an agent cannot get from the structured fields.

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?

Purpose, input requirement, and link-expiry are front-loaded, which is good, but the mid-section detailing Cloudflare R2 storage and the ihateaudio.com headless-browser pipeline is implementation trivia that does not help an agent invoke the tool correctly. The description could shed those sentences without losing 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?

With no output schema, the description correctly covers the return contract (download links that expire after 1 hour) and the input contract (one public HTTPS file). Given the nested file object and free-form settings bag, this is close to complete, though it stops short of clarifying the settings keys' accepted values.

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%, so the baseline is 3. The description restates the params (settings keys, outputFormat examples, bitrateKbps) but adds no format constraints or semantics beyond the schema — the 'settings' object keys (vocals, drums, bass, other) are named but their expected values remain undefined in both places.

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 resource ('Separates a song into stems') and enumerates the outputs (vocals, drums, bass, other), which cleanly distinguishes it from near-neighbors like vocal_remover and acapella_extractor. The mechanism ('by source separation') is named as well, so the agent knows exactly what operation is performed.

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?

Usage is implied by the purpose statement, but the description never says when to pick this over siblings such as vocal_remover (isolate the instrumental) or acapella_extractor (isolate vocals). No exclusions, prerequisites, or alternative routing are given, leaving the agent to infer the choice from the operation name alone.

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