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

Annotations already declare a non-destructive mutation (readOnlyHint=false, destructiveHint=false), which the description is consistent with. Beyond that, it discloses a genuine runtime behavior the annotations cannot express: the call is refused when a later edit overlaps the region being restored, plus the two ways out. It does not say whether the revert itself can be undone or what permissions are needed, which keeps it below a 5.

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 action and immediately followed by the undo contrast and the refusal caveat; nothing is padding. The wording is a little colloquial ("before you touched them") but does not cost clarity.

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-parameter mutation with no output schema, the definition covers the core action, one alternative, and one failure mode. It omits what happens to clips that were newly created by the reverted steps, whether the revert is itself reversible, and what the caller gets back, which are material for a non-destructive-but-mutating tool.

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 67%: steps and projectId are already documented in the schema, leaving only the boolean all undocumented. The trailing "or all" gestures at that parameter but is ambiguous about whether it means all steps or all conflicting edits, so the description only partially compensates. Baseline 3 is appropriate given the schema does most of 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?

The description names a concrete action (put clips back to their pre-step state) on a concrete resource (clips produced by listed steps), and explicitly contrasts it with the sibling tool undo ("undo only takes back the last one"). The phrasing "clips of some of your steps" is informal but still resolvable against the steps parameter, so an agent can distinguish it from undo and restore_version 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?

It states the selection condition against the obvious alternative (use this rather than undo when you need to roll back more than the last change) and gives recovery instructions when the call is refused ("revert that one too, or all"). It stops short of naming keep_changes/list_changes as workflow prerequisites in prose, leaving that to the schema's mention of list_changes.

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