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

Annotations already declare destructiveHint=true, but the description adds the substance the annotation cannot: exactly which record groups are deleted (combinations, loads, load cases, springs, supports, groups, elements, nodes, sections, material), that model units are restored, that preview is the default, and one irreversible edge case. That is precisely the what-gets-destroyed context a mutating tool needs.

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 sentences, front-loaded with the destructive scope, then the limitation, then the preview/apply rule. The parenthetical list is long but each item is informative rather than filler.

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 two-parameter destructive mutation with no output schema and full annotation coverage, the description covers scope, reversibility, and preview behavior adequately. The remaining gap is runId semantics and what the returned preview looks like, though no output schema exists to relieve that.

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%, so the description must carry the parameter burden. It explains apply well ("Previews unless apply: true"), but runId is never mentioned — an agent cannot tell from this text that runId selects which build run to revert, nor what happens if it is omitted.

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 gives a specific verb (deletes rows) applied to a precisely named resource (everything culvert_build wrote), and enumerates the record types touched. Naming culvert_build ties it to its counterpart sibling, so an agent can distinguish this undo tool from the other *_undo tools in the list.

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?

"Previews unless apply: true" tells the agent the default invocation is a dry run, which is direct usage guidance, and "A model replaced by newDocument cannot be brought back" states an explicit exclusion where the tool is useless. What is missing is a plain statement of when to reach for undo versus rebuilding with culvert_build.

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