unload_playlists

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

With no annotations, the description carries the full burden and does it well: it discloses that nothing changes on Spotify, that the operation is reversible via load_playlists, that orphaned tracks and artists are also evicted, and that affected drafts are modified. Those cascade and side-effect details are exactly the behavioral context an agent needs before a state-changing call.

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 the core action and its reversibility, then the cascade caveat, then argument formats. Every clause adds distinct information; nothing repeats the tool name or the schema title.

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 single-parameter, no-output-schema mutation tool, the description covers the action, its scope boundary, its side effects, its undo path, and the accepted argument formats. It even notes that the remaining-overview is displayed, covering the user-visible result the absent output schema would otherwise leave unexplained.

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% – the schema only says 'array of strings' – but the Args block explains that entries may be playlist names, a unique fragment of a name, IDs, or Spotify links. That adds real disambiguation meaning (partial-name matching, link acceptance, uniqueness requirement) that the schema cannot convey.

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?

Names a specific verb and resource ('Take one or more playlists out of the local cache') and states the scope precisely: removal from local analysis only, not from Spotify. It explicitly distinguishes itself from the sibling load_playlists, which is the natural inverse, so an agent can route without opening either schema.

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 makes the use case clear (drop playlists from the current analysis) and names load_playlists as the way back, which implicitly tells the agent when not to worry about data loss. It does not explicitly contrast with forget_my_data or state preconditions such as the playlist being currently loaded, which keeps it from a 5.

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