rollback_file

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

With no annotations, the description carries the full burden and does answer the key question for a mutation tool: the current state is snapshotted first, so the rollback is reversible. It does not address permission or lock prerequisites (relevant given lock_file/check_lock/unlock_file siblings), nor concurrency effects on other editors, so it falls short of fully transparent.

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?

It is front-loaded with the action and the safety guarantee, and each clause adds an operational fact. The "UNDO YOUR MISTAKE" preamble is stylistic padding but costs only a few words and does reinforce intent.

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 three-parameter mutation tool with no annotations and no output schema, the description covers the essentials: scope (shared project), the default behavior, the two-step path for targeting a version, and reversibility. Only permission/lock prerequisites and post-rollback state are omitted.

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 100% and both optional parameters already document "Omit to undo last change," so the description mostly restates the schema's default semantics. It adds the useful constraint "pass ONLY path" but never mentions change_id or the mutual exclusivity of change_id vs snapshot_id, so it does not meaningfully enrich parameter meaning beyond what is already structured.

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?

"Restore a shared-project file to a previous version" names a specific verb and resource, and the "UNDO YOUR MISTAKE" framing immediately distinguishes it from the editing siblings (edit_file, write_file) which change content forward rather than reverting it.

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 explicit branching: pass ONLY path to undo the last change, or call list_snapshots first and then pass path + snapshot_id for a specific version. The alternative tool is named along with the ordering constraint that selects it, leaving nothing to inference.

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