purge

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

With no annotations, the description carries the full burden and does so well: it discloses the dry-run default, the refusal condition when Traktor is running, the automatic single backup taken beside the collection before writing, and the cascading effects on playlist references, history, cues and play counts. These are exactly the mutation risks an agent needs before invoking.

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?

A single dense paragraph where every clause carries information — scope, side effects, dry-run default, refusal, backup. The most safety-critical fact (dry run by default) is bolded mid-paragraph rather than front-loaded, which is the one structural miss.

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?

An output schema exists, so the 'reported' results needn't be enumerated, and the description covers side effects, prerequisites and write safety. Minor gap: it doesn't indicate how an agent should determine whether Traktor is running (the sibling 'status' tool) before retrying a refusal.

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 0% and the sole parameter 'apply' is undocumented in the schema, but the description supplies its complete meaning: the operation is a dry run unless apply is true. That fully compensates for the coverage gap; only the boolean's explicit false default is left to the schema.

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?

Specific verb and resource: removes collection entries whose backing files no longer exist, with the rationale ('a collection is an index of files that exist'). It's unambiguous what the tool does, though it never names the sibling tools (plan/apply/status) that overlap with the dry-run-vs-write distinction, leaving an agent to infer 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?

Gives a clear triggering condition (residue from deleted files) and states the default operating mode ('Dry run unless apply is true'), plus a hard prerequisite ('Refuses while Traktor is running'). It stops short of saying when to prefer the sibling 'plan' or 'apply' tools instead of this one.

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