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

Annotations declare a non-read-only, non-idempotent, non-destructive operation, and the description adds genuinely useful context beyond that: the server downloads the input, the input is held in Cloudflare R2 and processed headlessly, the input is deleted when the job ends, and output links expire after one hour. These lifecycle facts are not in the annotations. It does not cover failure/retry behavior.

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?

Dense and front-loaded: the action, the input contract, the settings, and the output/lifecycle follow in a logical order. Slightly overpacked with implementation detail (Cloudflare R2, ihateaudio.com headless browser) that competes with actionable information, but every sentence carries 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?

For a single-input effect tool with no output schema, the description covers the input source, processing pipeline, output link lifetime, and input deletion. The main gap is the meaning and constraints of the four reverb settings, which are listed but unexplained.

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 coverage is 100% and the schema already documents download_url, file_id, bitrateKbps, and outputFormat. The description adds the names of reverb settings (space, decaySec, mix, preDelayMs) but not their semantics, ranges, or defaults, and the settings object schema is unbounded with no property descriptions. That leaves the reverb controls documented only by name 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?

The description states a specific verb and effect: 'Adds convolution reverb.' That distinguishes it from effect siblings like echo_adder and slowed_reverb, though it never names those alternatives. Purpose is clear without sibling routing.

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 input contract ('one file with a public HTTPS download_url') and the optional reverb settings, but there is no explicit when-to-use, when-not-to-use, or ranking against the large set of audio-effect siblings. A competent agent can infer it, but the description provides no guidance beyond the mechanics.

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