undo_list

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

No annotations are provided, so description carries full burden. It discloses key behaviors: `truncated` is measured by fetching an extra row, not guessed; `effectVerified=false` means the change is probable not confirmed; `target` is unused. This is far beyond what structured annotations would provide, giving agents crucial decision-relevant context about response handling and safety.

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 thorough but well-structured with a clear opening, a return format example, behavioral notes on `truncated` and `effectVerified`, and an Args section. Every sentence adds value; no filler. Front-loaded with the core purpose, then semantic details.

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 tool with no output schema and no annotations, the description provides a complete picture: return format, field semantics, edge-case handling, and parameter usage. It also integrates with sibling `undo_apply` by referencing it. This is fully self-contained for an agent to decide when and how to invoke it 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 0%, so description must compensate. It explains `limit` (default 50, capped at 500) and `target` (unused but accepted for uniformity), which fully covers both parameters' meaning and constraints. A slight deduction because it doesn't explicitly mention that `limit` is an integer max rows, but that's clear from 'Max rows to return' and the 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?

The description opens with '[READ] List recorded, not-yet-applied undo tokens (most recent first)', specifying the verb 'List', the resource 'undo tokens', and the state (recorded, not-yet-applied). It also distinguishes from sibling `undo_apply` by noting it lists tokens for that tool. This is a specific, clear purpose that differentiates it from 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?

Explicitly states when to use: to list undo tokens and to obtain `undoId` for `undo_apply`. It also gives guidance on truncated results and the `effectVerified` field, telling users when to re-run with higher `limit` and to check live state before applying. This covers both usage context and alternatives (`undo_apply`), and provides behavioral exclusions (e.g., not to report unverified effects as confirmed).

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