undo_apply

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

Annotations already declare non-read-only, non-idempotent and destructive, and the description adds meaningful context beyond them: the inverse runs through its own governed/audited tool, dry_run previews without executing, and 'a token can only be applied once' explains the one-shot semantics. It does not say what happens on partial failure or whether the undo is itself reversible, keeping it below a 5.

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?

Front-loaded with the [WRITE][risk=medium] tag followed by the core mechanism in the first sentence, then the preview and one-shot constraints, then a compact Args block. Every sentence carries information; the Args section mildly duplicates the schema titles but adds origin/behavior notes.

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 3-param mutation tool with no output schema, the description covers the mutation path, auditing, preview, and idempotency-limit. Missing are error/rollback behavior and the concrete return of a dry_run preview, but the essentials for correct invocation are present.

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 the description carries the full burden and mostly does: undo_id is defined by origin, dry_run by effect, and target by pass-through behavior. The target semantics are a bit thin (which tools accept it, what values), but all three params get meaning the 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?

States a specific verb+resource ('Apply a recorded undo') and immediately explains the mechanism ('dispatching its inverse tool'), which distinguishes it from the sibling undo_list that produces the tokens. An agent can tell what this does without opening the schema.

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?

Points to the source of the required argument ('the undoId from undo_list (or an _undo_id in a write result)'), which implicitly routes the agent through undo_list first, and describes the dry_run preview path. It stops short of explicit when-not-to-use guidance or naming alternatives, so it is clear context rather than full routing.

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