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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds critical behavior beyond that: refusal conditions tied to dependent elements, the default run selection, and preview-vs-apply semantics. This is exactly the extra context an agent needs for a destructive 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?

Four dense sentences, each carrying distinct information: what it reverses, the refusal precondition, the default target, and preview semantics. Front-loaded with the core action and no 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?

No output schema exists, but the description covers the destructive effects, safety preconditions, default targeting, and preview behavior — everything needed to invoke a destructive undo correctly.

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% (only runId documented), but the description compensates: it explains that apply:true commits versus default preview, and that runId defaults to the latest un-undone create_nodes run. Both parameters gain meaning beyond the raw schema.

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 ('Reverses') and resource ('a create_nodes run from the ledger'), then details the exact effects: deletes created nodes and restores overwritten nodes to earlier coordinates. This clearly distinguishes it from the sibling create_nodes 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?

Explicitly states a precondition ('Refuses while elements, structure groups or supports use the nodes it created (undo those first)') and clarifies the default target ('the latest create_nodes run not yet undone'). It doesn't name specific sibling undo tools, but the when/when-not conditions are clear.

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