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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds genuinely new behavioral semantics beyond that: the undo is conditional and per-item, reverting each change 'only while it is still what the agent wrote', which tells the agent partial/stale reverts are possible. It omits any auth requirement or reporting of partial success.

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?

Two sentences, front-loaded with the core action and scope; the artifact enumeration is dense but each item earns its place by defining the scope boundary. No filler or restatement of the title.

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 single-parameter mutation with no output schema, the description covers scope, conditional behavior, and the relationship to apply_turn. It could still say what a partial revert looks like to the caller, but nothing essential prevents 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 100% and the single parameter's provenance ('from send_message or get_chat') is already documented in the schema. The description adds no syntax, format, or validation detail for turn_id, so this is the baseline case where the schema does the work.

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 ('Revert') and a precisely scoped resource ('what a turn changed OUTSIDE the canvas'), then enumerates the affected artifact types. It also distinguishes itself from the sibling apply_turn by explaining that canvas proposals are not landed without apply_turn and therefore need no undo here.

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 a clear when-to-use condition (revert turn changes outside the canvas) and a when-not-to condition (canvas changes, which require apply_turn to land at all). It does not discuss the sibling recovery tools retry_turn/stop_turn or warn about irreversibility, so it stops short of full alternative routing.

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