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

Goes well beyond the destructiveHint/openWorldHint annotations, disclosing the exact deletion order (elements then nodes), the fingerprint guard that preserves anything edited since the import, the rule keeping nodes still used by other elements, and the conditional unit restore. The only gap is the shape of the non-preview response, but the annotations already flag destructiveness and the description adds rich behavioral context.

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-loads the core action in the first clause and packs the rest with substantive rules rather than filler. It is dense and long, but each clause carries a distinct behavioral fact; slight tightening of the nested parentheticals would help readability.

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 two-parameter tool with no output schema, it covers preconditions, default targeting, safety behavior, and what the preview reports. Only the committed-run return value is left implicit, which is a minor gap given the preview is described.

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 50% (apply has no schema description), and the description compensates by explaining that apply: true commits while the default previews what would be removed and kept. It also explains the runId default (latest un-undone import), giving meaning beyond the schema's "The runId dxf_import returned."

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 and resource ("Removes what one dxf_import created") and immediately frames it as an undo of a named sibling, so the agent can distinguish it from dxf_import, dxf_inspect, and unrelated *_undo tools. The scope statement is precise about what is removed and under which rules.

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?

Gives explicit preconditions and exclusions: it "refuses unless the import's master group is in the open model," works after a partial import, and defaults to the latest not-yet-undone import when runId is omitted. It also spells out the safe path — preview by default, mutate only with apply: true — leaving nothing to inference about when to call it.

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