Forget a learned label or artist

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds useful context — this is a repair path and it only affects learned, not seed, entries — but it does not say what happens if neither label nor artist is supplied, whether a removal can be undone, or whether both can be removed in one 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?

Three short sentences, each doing distinct work: framing the operation as repair, excluding the seed case, and constraining usage. The repair framing and the exclusion are front-loaded ahead of the caution.

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 destructive three-parameter tool with no output schema and low schema coverage, the definition resolves the seed-versus-learned distinction but leaves the label/artist selection rule and the post-removal state unstated. An agent can call it, but may call it incorrectly by omitting both targets or passing both.

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 33%: only 'lane' is documented in the schema. The description implies 'label' and 'artist' are the removable targets, which clarifies their role but not whether exactly one must be provided, what happens if both are passed, or what an empty call does.

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 uses a specific verb ('remove') and resource ('a label or artist the lane learned'), and it is framed as a repair operation. It clearly distinguishes the learned-entry case from seed labels/artists, which are edited in lanes.json rather than through this tool.

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?

It gives both a positive condition ('repair') and an exclusion ('seed labels and artists are edited in lanes.json instead'), plus the restraint 'Only use when asked.' What's missing is a named sibling alternative or a statement of when a learned entry should be corrected some other way.

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