undo_apply

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds substantial context: the inverse runs through its own governed tool with its own risk tier and audit row, a token can only be applied once (reinforcing non-idempotency), and dry_run previews without executing. These are behavioral facts beyond the annotation flags.

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 risk tag and core behavior are front-loaded, and the prose is tight. The Args block partly restates dry_run and target already covered above, a minor redundancy, but each section remains short and readable.

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?

There is no output schema and no annotation coverage of audit/authorization semantics, yet the description covers the mutation, the single-use constraint, the preview path, and where the audit record lands. What dry_run actually returns is described at a high level; enough for correct invocation.

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 full parameter burden and largely succeeds: undo_id is tied to its source, dry_run is defined as a non-executing preview, and target is explained as a pass-through to the inverse tool. The only gap is that 'target' itself is never defined (table? session?).

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 applies a recorded undo by dispatching the inverse tool. It clearly distinguishes itself from the sibling undo_list, which is named as the source of the undo_id, so an agent can tell the two apart without opening either 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?

It gives clear context for use: obtain undo_id from undo_list (or an _undo_id in a write result), and it explains the dry_run=True preview path. It does not state explicit when-not conditions or alternatives beyond undo_list, so it falls just short of the top band.

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