undo_apply

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation risk is covered structurally. The description adds real value beyond them: the medium risk tier, the fact the inverse runs through its own governed tool, and the crucial constraint that a token can only be applied once (reinforcing non-idempotency).

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, a one-line purpose, then a clean Args block. Every sentence earns its place; only the bracketed meta-tag is slightly noisy.

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 tool with no output schema, the description covers purpose, arg sources, preview mode, and the single-use constraint. Minor gaps remain on what happens if a token is expired or already consumed, but it is largely self-sufficient.

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 must carry the burden, and it documents all three parameters: undo_id (its source), dry_run (preview behavior), and target (passed through to the inverse tool only when accepted). This meaningfully compensates for the bare schema.

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 being the action that consumes a token produced elsewhere. 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?

Gives concrete usage context: undo_id comes from undo_list or an `_undo_id` in a write result, and dry_run=True is recommended to preview before executing. There is no explicit when-not guidance, but the guidance present is specific and actionable.

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