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

Annotations only cover the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), while the description adds substantial non-obvious behaviour: output download links expire after 1 hour, the server fetches the file from download_url, stores it in Cloudflare R2 during the job, processes it in a headless browser, and deletes the input when the job ends. These lifecycle and storage facts are exactly the context an agent cannot get from structured fields. No contradiction with annotations.

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 requirements are front-loaded, and the sentences on link expiry and input deletion clearly earn their place. The infrastructure sentence about R2 storage and a headless browser on Cloudflare is less decision-relevant but does not bloat the text excessively.

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 the return value (download links that expire after 1 hour) and the input contract (public HTTPS download_url). It is nearly complete, though it does not clarify behaviour when multiple files are supplied despite the schema allowing up to 12 items.

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 files, settings, bitrateKbps and outputFormat. The description largely repeats this (settings keys, outputFormat examples) but does add one useful qualifier — that outputFormat and bitrateKbps apply 'where the tool supports them' — so it sits at the baseline rather than below it.

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 a specific verb and resource ('Makes an audio file smaller') and names the mechanism (lowering bitrate, sample rate or channel count), which usefully distinguishes it from dynamic_compressor and the various *_converter siblings. It never explicitly names or excludes a sibling, so it stops just 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?

Usage is implied by the purpose statement: reach for this when you want a smaller audio file via reduced bitrate/sample rate/channels. However, there is no explicit when-to-use guidance and no routing advice versus near-neighbours like audio_converter, sample_rate_converter or stereo_to_mono, leaving selection to inference.

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