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

Beyond the annotations (readOnlyHint=false, non-idempotent, non-destructive), the description discloses genuinely useful behavior: the server downloads the URL, stores it in Cloudflare R2 during the job, processes via a headless browser, and deletes the input when the job ends. The 1-hour expiry on result links is a critical operational detail not captured anywhere in the schema.

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 and input are front-loaded, and the lifecycle/expiry sentences earn their place. The backend implementation detail (headless browser, Cloudflare R2) is somewhat beyond what an agent needs to invoke the tool correctly, but the description stays readable in one paragraph.

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 it returns download links that expire after 1 hour, and it covers input requirements and job lifecycle. It is nearly complete, with only the missing explicit sibling routing keeping it from a 5.

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 parameters are already documented, making 3 the baseline. The description restates outputFormat examples already present in the schema and adds only the soft qualifier "where the tool supports them" for outputFormat/bitrateKbps, which is marginal added meaning.

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 gives a specific verb and resource ("Isolates the vocals from a song by source separation and returns the vocal track"), which is clearly distinct in meaning from a stem splitter or converter. However, it never names the obvious sibling (vocal_remover) whose function is the inverse, leaving that routing to inference. Clear purpose, but no 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?

It states input constraints (one file, public HTTPS download_url), which implies usage but never says when to pick this tool over vocal_remover (which keeps the instrumental) or stem_splitter (all stems). No exclusions or alternative routing are given, so the agent must infer the choice.

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