Rollback Agent Session

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

Annotations only flag destructive/idempotent/openWorld; the description adds substantial detail beyond them: soft-delete vs restore vs revert semantics per change type, unit-of-work behavior, and the explicit carve-out that templates/settings are not auto-reverted. This is exactly the added behavioral context the dimension rewards.

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 the core action, then the per-type semantics, then the caveat. Three dense sentences with no filler; slightly long but each clause carries information.

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?

No output schema exists, and the description covers the mutation's behavior thoroughly enough for correct invocation. The one gap is that it doesn't describe what the 'listed for manual review' output looks like, but that is minor for a rollback 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 100%, so the parameter is already documented, but the description adds the meaningful default semantics ('Defaults to this MCP session's own ID', i.e. 'undo everything I did') that the schema does not convey as behavior.

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 precise verb (undo/rollback) and resource (every content change from an agent session) and goes further by enumerating the exact semantics: creates are soft-deleted, deletes restored, updates reverted. It is clearly distinct from siblings like get_agent_session_changes and end_agent_sandbox.

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?

Explicitly frames the default case ('undo everything I did') and clarifies scope limits (non-content changes are only listed, not reverted). It gives clear context for when to call it, though it doesn't explicitly name a preview alternative such as get_agent_session_changes before committing.

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