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

Annotations cover only the safety profile (readOnly=false, destructive=false, openWorld=false, idempotent=false), but the description adds genuinely useful lifecycle detail: the server downloads the file, stores it in R2 during the job, deletes the input at job end, and the returned links expire after 1 hour. It omits expected processing duration and failure behavior, which keeps it from a 5.

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 is front-loaded in the first clause, followed by params, return behavior, and lifecycle. The Cloudflare R2 / headless-browser implementation detail is somewhat expendable for an agent choosing a tool, but it is contained and does not bury the actionable 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 fills the gap by explaining that download links are returned and expire after 1 hour. Input constraints and format options are covered; only processing time expectations and error handling are missing.

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 schema already documents download_url, file_id, outputFormat and bitrateKbps. The description largely repeats this ('Optional outputFormat ... and bitrateKbps'), adding only the mild hint 'where the tool supports them' for format support. Baseline 3 applies when the schema carries the weight.

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 ('Removes the vocals from a song by source separation and returns the instrumental'), and the output wording implicitly distinguishes it from acapella_extractor (which yields vocals) and stem_splitter (which yields multiple stems). Siblings are not named explicitly, so it stops short of a 5.

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 conveys input constraints ('one file with a public HTTPS download_url') that imply when the tool is usable, but it never states when to choose this over acapella_extractor or stem_splitter, nor any exclusions. Usage is inferred rather than stated.

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