undo_apply

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

Annotations declare destructive=true and idempotent=false; the description adds real context beyond them – the inverse is dispatched through its own governed tool and audited under its own risk tier, dry_run previews without executing, and a token can only be applied once. These are material behavioral facts an agent needs.

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 a [WRITE][risk=medium] tag, then purpose, behavioral notes, and a compact Args block. Every sentence earns its place given the 0% schema coverage, though it is slightly verbose in places.

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 destructive, non-idempotent mutation with no output schema, it covers preview, single-use, and audit routing. The return shape of a dry_run preview is only lightly described, leaving a minor gap, 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 description coverage is 0%, so the description carries the burden and documents all three params: undo_id (its origin), dry_run (preview semantics), and target (pass-through to the inverse tool when accepted). It adds genuine meaning, though it doesn't fully specify types or edge behavior.

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 by dispatching its inverse tool') and distinguishes itself from the sibling undo_list by naming it as the source of the undoId. An agent can tell immediately what this does versus merely listing undo tokens.

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?

Gives clear operating context: obtain the undoId from undo_list (or an `_undo_id` in a write result), pass dry_run=True to preview, and note that a token is single-use. It stops short of explicit when-not-to-use guidance, but the workflow is unambiguous.

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