nx_undo

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

No annotations are provided, so the description carries the full burden. It identifies the tool as an undo (a mutation), but does not disclose what the transaction reverts, whether the undo itself is reversible, what side effects occur, or what permission/state checks are needed. That is a significant gap for a destructive tool.

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?

A single sentence with no filler, the key verb front-loaded and the sequencing advice kept short. Every word contributes to the core message.

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?

The signature is simple, but the absence of annotations and an output schema means the description should explain side effects, return behavior, and the meaning of transactionId. It does not, leaving an agent to guess the consequences of calling it.

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% and the description never mentions transactionId. The schema shows an optional UUID, but the agent cannot tell whether supplying it targets a specific transaction instead of the most recent one or what the default behavior is.

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 names a specific action ('Undo'), a clear resource ('the most recent dsh-nx transaction'), and a scope qualifier. No sibling tool appears to perform an undo, so an agent can distinguish it from the create/measure/preflight tools without further info.

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 only guidance is the sequencing instruction 'after inspecting current state', which tells the agent to verify before reverting. However, it never states when an undo is appropriate, when to avoid it, or how transactionId selects a different transaction; no alternative tools are mentioned.

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