undo_list

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

With no annotations, the description carries the full burden and excels. It reveals the exact return shape, explains that `truncated` is *measured* (one extra row fetched) rather than inferred, and defines `effectVerified` semantics (PROBABLE vs confirmed). It also discloses that `target` is unused and state is host-local. This is exceptionally transparent behavior beyond basic schema info.

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 well-structured: a concise summary line, followed by return format and edge-case explanations, then a clean Args list. Every sentence adds value; no fluff or repetition. The length is justified by the technical nuance it conveys.

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?

Despite having no annotations or output schema, the description covers purpose, parameters, return values, edge cases (`truncated`, `effectVerified`), and usage workflow. It is fully self-contained for an agent to select and call the tool correctly, and even explains how to interpret results for downstream actions.

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% in the structured schema, but the description's Args section fully compensates: `limit` is described as max rows with default 50 and cap 500, and `target` is explicitly documented as unused/accepted for CLI uniformity. This adds crucial meaning that the bare schema lacks.

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 opens with a clear, specific verb and resource: '[READ] List recorded, not-yet-applied undo tokens (most recent first).' It distinguishes itself from sibling `undo_apply` by stating it lists tokens for later application, and it names the inverse tool behavior. The purpose is unmistakable.

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?

Provides practical usage guidance: tells the agent to use `undoId` with `undo_apply`, explains the `truncated` flag ('re-run with a higher `limit`'), and warns about `effectVerified` false (check live state before applying). It does not explicitly state when not to use the tool, but the context and details imply appropriate usage clearly.

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