taste_checkpoint_diff

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

With no annotations provided, the description carries the full disclosure burden and does meaningful work: it states the tool is purely local, makes zero API calls, and describes the kind of analysis produced. It does not cover edge cases like missing checkpoints or clarification of the list-slots behavior, but the core behavioral profile is clearly disclosed.

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?

The description is compact and front-loaded with the main purpose, followed by the important local/no-API trait. The final sentence 'List slots with from="?" or omit' is a bit cryptic and awkwardly punctuated, but it is short and carries extra functional information.

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 tool with no output schema and no annotations, the description covers the operation, the computed diff dimensions, and the special list-slots invocation. It does not fully explain return shape, label syntax, or prerequisite checkpoints, but the core invocation behavior is understandable enough for an agent to use and discover the rest.

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 100%, so the baseline is 3, but the description adds a hidden usage pattern not in the schema: passing from='?' or omitting it to list checkpoint slots. This is valuable extra semantics. The other parameters remain well-covered by the schema descriptions.

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 names a specific verb and resource: 'Diff two saved taste checkpoints', and lists concrete outputs: new entrants, drop-offs, genre drift, and Jaccard similarity. The 'Pure local sidecar — zero API calls' phrasing also distinguishes this from API-backed sibling tools like diff_playlist_snapshots or library_snapshot_diff.

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 useful context: it is a local sidecar with zero API calls, implying it is appropriate for offline or lightweight comparisons of saved checkpoints. It also hints at a list-slots mode with 'from="?" or omit'. However, it does not explicitly state when to prefer this over related diff/snapshot tools or when not to use it.

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