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

With annotations only covering the generic safety flags, the description adds substantial behavioral detail: the server fetches from download_url, holds the intermediate in Cloudflare R2, processes via a headless browser, deletes the input when the job ends, and returns download links that expire after one hour. It also notes outputFormat/bitrateKbps are only honored 'where the tool supports them.'

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?

Front-loaded with purpose, target examples, and the input contract, then lifecycle and return behavior. The infrastructure sentence (R2/Cloudflare headless browser) is the one stretch of implementation detail, but it still conveys relevant processing context.

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 mutation tool with no output schema and a passthrough settings object, the description covers everything an agent needs: required input shape, target semantics, format options, the 1-hour link expiry, and the fact that the source file is not retained. Nothing material is 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 coverage is 100%, so the baseline is 3. The description restates the settings keys (platform, targetLufs, ceilingDbtp) that the schema already lists and adds little syntax or valid-range detail; its only genuine addition is the caveat that bitrateKbps applies only to supported formats.

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+resource ('Normalizes loudness to a LUFS target') with concrete target examples (-14 Spotify, -16 podcasts) and a true-peak ceiling, making it clearly distinct from the neighboring loudness_meter and volume_booster. It never names a sibling explicitly, so it stops short of full 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?

Platform-target examples imply the use case (streaming/podcast loudness compliance), but there is no explicit 'use this when...' guidance and no mention of when to prefer loudness_meter or volume_booster instead. Usage is inferable rather than stated.

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