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

Annotations already declare destructiveHint=true, so the safety profile is known. The description adds genuinely new behavior beyond that: the operation is atomic ('all or nothing') and will fail if any imported item has been modified since the import. This is exactly the kind of failure-mode context an agent needs before invoking a destructive batch operation.

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 short sentences, front-loaded with the action and its scope, followed by the constraint. No filler wording.

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 one-parameter destructive tool with no output schema, the description covers what is removed, the atomicity, and the precondition for failure. The main remaining gap is not saying what a successful result looks like or how an agent recognizes and obtains a valid batch id.

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% for the single parameter, but the description compensates by explaining that 'batch' means the id of one prior import, which the bare schema does not say. It does not say where to obtain that batch id or its format, so the compensation is partial.

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?

States a specific verb ('Removes') and a scoped resource ('everything one import added'), which implicitly separates it from the sibling trainrec_undo_change that undoes a single change. It never names the sibling, so the differentiation is inferred rather than stated.

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 a clear precondition for calling it (a batch id from an import) and a clear refusal condition ('refused if any of it has been edited since'). It does not tell the agent what to do instead when the undo is refused, e.g. whether to fall back to trainrec_undo_change, so guidance stops short of explicit alternatives.

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