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

With no annotations, the description carries the burden and does well: it discloses cost (1 credit per minute of output), asynchronous behavior (long jobs return a job_id to poll via get_job), and result-link expiry (1 hour). It omits auth/permission requirements and failure behavior, but the pricing, async, and expiry disclosures are substantive operational context.

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?

Four short sentences, front-loaded with the purpose, then preset detail, then options, then operational constraints. Tight and well ordered, with only mild redundancy between the preset sentence and the schema's own preset description.

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 13-parameter tool with no annotations and no output schema, the description supplies the missing operational layer: cost, job_id polling, and result-link expiry, which effectively explains the return path. Remaining gaps are per-parameter detail and any mention of input constraints or auth needs.

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 62%, so roughly a third of the 13 parameters lack descriptions (format, speed, mono, fades, start/duration). The description compensates partially by naming the adjustable operations and stating the preset's -16 LUFS target and that normalize_lufs overrides it, but it says nothing about start_seconds, duration_seconds, or output format choices.

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 ('audio cleanup') plus a concrete capability list (denoise, silence trim, loudness leveling, volume, fades, speed, mono). It is clear what the tool does, but it never distinguishes itself from siblings like trim_media, convert_media, or compress_media, which overlap with trimming and format conversion.

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 rather than stated: 'one-step audio cleanup' and the preset enumeration signal the intended scenario, and polling with get_job is explicit guidance. However, there is no when-to-use/when-not-to-use framing and no routing to sibling tools for overlapping tasks such as trimming or format conversion.

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