undo_apply

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, so the safety profile is covered. The description adds genuine context beyond them: the inverse runs through its own governed/audited tool with its own risk tier, and the token is single-use, which sharpens the non-idempotent semantics. It doesn't state whether the applied undo is itself reversible.

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-loads the [WRITE][risk=medium] signal, then the core behavior in one sentence, followed by a compact Args block. Every sentence earns its place given the 0% schema coverage; slight redundancy between the prose and the staged dry_run note keeps it from a 5.

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 write tool with no output schema, the definition covers action, mechanism, idempotency limit, preview mode, and all parameters. The one unaddressed item is what a successful (non-dry_run) call returns, but with no output schema and dry_run described, the agent has enough to call 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 the description carries the burden and mostly succeeds: undo_id is documented with its source (undo_list or _undo_id), dry_run is defined as previewing the inverse tool+params, and target is described as passed through only when the inverse tool accepts one. Minor gaps remain on target's type/format, but all three params get meaningful semantics.

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 and resource ('Apply a recorded undo by dispatching its inverse tool') and immediately distinguishes itself from the similarly named sibling undo_list by defining apply as the execution counterpart to listing. An agent can tell exactly 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?

Explicitly tells the agent where to get the required undo_id ('from undo_list (or an _undo_id in a write result)') and documents the dry_run preview path as an alternative to executing. It stops short of stating when NOT to apply an undo, but the routing to undo_list covers the main selection question.

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