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

Annotations already declare this as destructive and not read-only. The description adds useful behavior beyond that: restoration comes from a snapshot taken just before the original write, and the tool previews unless apply is true. It does not cover edge cases such as invalid run IDs or repeated undo, but it is informative.

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?

The description is compact and front-loaded: it defines the operation, the data source, the default target, and the preview/apply switch in two dense sentences with no wasted text.

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 undo tool with annotations already flagging destructiveness and no output schema, the description supplies the key call context: what is restored, from which snapshot, which run is default, and that preview is the default. Missing details concern edge cases rather than the core behavior.

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 description coverage is 0%, so the description must carry parameter meaning. It explains apply semantics (preview unless apply=true) and the runId default (latest run not yet undone). It could say more about the runId format, but both parameters are meaningfully addressed.

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 states a specific verb and resource: it restores rows changed by a stage_groups or construction_stages run. Naming those two source tools clearly distinguishes it from the many other *_undo siblings.

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?

It gives clear context for use: undo a stage_groups or construction_stages run, defaulting to the latest run not yet undone, with preview unless apply is true. It does not explicitly rule out use for other run types or name alternatives, but the scope is clear enough.

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