clean_all_playlists

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It explicitly states the default read-only reporting behavior, that apply=true mutates by removing duplicates, that the first occurrence is kept, and that a single confirmation precedes deletion. It also discloses the optional relinked-track behavior. This is unusually transparent for a destructive tool.

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?

Two concise sentences carry high information density with no filler. The core function and scope appear first, followed by the crucial default/apply behavior and the confirmation safeguard. Every sentence earns its place.

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?

The description is largely complete for a destructive library-wide cleanup tool: it covers scope, default behavior, mutation trigger, retention rule, confirmation, and the opt-in relinked detection. There is no output schema, so a tiny gap remains around what the per-playlist report actually contains beyond 'findings,' and it does not mention response_format or max_results, though those are documented in the schema. Overall, the agent has enough to call the tool safely.

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?

The input schema already covers all four parameters with descriptions and defaults, so the baseline is 3. The description adds meaningful context for apply (removal with confirmation) and include_relinked (same-song copies under different URIs), but it does not add anything about max_results or response_format. Because the schema already provides full parameter documentation, scoring above the baseline is not necessary.

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 clearly states the action: scan every playlist in the library for duplicate items and optionally remove them with apply=true. It names the resource scope (all playlists) and the domain (duplicates, including relinked songs). It does not explicitly name sibling tools like find_duplicates_in_playlist or find_duplicate_tracks_across_playlists, so differentiation from those is left implicit, but the purpose is unmistakable.

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 provides useful operational guidance: report-only by default, apply=true to remove, and one confirmation for bulk removals. However, it does not explicitly state when to choose this tool over related sibling tools such as find_duplicates_in_playlist, find_duplicate_tracks_across_playlists, or playlist_dedupe_advanced. The usage context is implied by 'every playlist in your library' rather than stated as an explicit selection rule.

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