unreal_apply

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

Beyond annotations, it reveals that the operation is undoable ('editor Undo transaction'), does not persist to disk, and must not be auto-retried after timeouts. These traits materially affect how an agent should invoke and monitor the call, and they do not contradict readOnlyHint, idempotentHint, or destructiveHint.

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?

Three short sentences convey the main operation, undo/persistence behavior, and critical guardrails. Every sentence earns its place, with the most important information front-loaded.

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 one-parameter apply operation with an output schema and annotations, the description covers the operation, undo/persistence behavior, authorization, staleness, and timeout handling. The only notable omission is explicit guidance on sourcing or verifying plan_id, but the workflow context and sibling tools make this inferable.

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?

The description adds modest meaning by identifying plan_id as a reviewed preview plan and warning that plans may become stale or expire. With 0% schema description coverage, it does not fully compensate by saying where the plan_id comes from or how it is obtained, but the single self-describing parameter limits the gap.

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 clear action ('apply'), a specific object ('reviewed preview plan'), and a distinctive execution mode ('once as an editor Undo transaction'), so an agent can tell apply apart from planning/preview tools. It does not explicitly call out the sibling unreal_workflow_apply, which keeps it from being a 5.

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 clearly states the only authorization condition ('Call only for edits the user authorized'), defines when a plan is unusable ('stale/expired plan requires a new preview'), and gives an explicit negative instruction about timeout retries. This is strong routing and handling guidance even though it does not name sibling tools.

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