Master a track

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

The description discloses substantial behavior beyond annotations: token cost with quota fallback ("COSTS 1 TOKEN when the account has a balance; otherwise it runs on the free quota without PRO modules"), async job semantics with timing ("typical 20-60 s, up to 10 min with restoration"), and a 100 MB server-side file ceiling. This is exactly the kind of context annotations (readOnlyHint=false, openWorldHint=true) cannot express.

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 dense sentences, front-loaded with the core purpose, then cost, then async workflow, then limits, then the recommendation. Every sentence carries distinct information — cost, timing, file ceiling, dry-run advice — with zero filler or repetition of schema content.

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 12-parameter, paid, asynchronous tool, the description covers the critical operational facts an agent needs: pricing model, quota behavior, async return pattern, expected latency, size limits, and a safe-first workflow. An output schema exists, so return values need no description, and the dry_run advice addresses the main risk of accidental spend.

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 92%, so the schema does most of the work. The description adds genuine meaning beyond it: the dry_run recommendation explains its purpose (price + effective settings before anything is spent) and the 100 MB ceiling adds a real constraint on audio_url that the schema omits. These are modest but concrete additions.

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?

"Master one track" names a specific verb and resource, and the explicit singular phrasing differentiates it from the sibling batch_master without needing to open either schema. The opening sentence is unambiguous about what this tool does.

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 gives clear operational guidance: run dry_run=true first for a price/settings preview, and expect to poll get_job afterward with concrete timing bounds. It does not explicitly state when to prefer siblings like batch_master or clean_ai_trace, though the "one track" phrasing implies the contrast.

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