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

The description transparently explains destructive effects, undo behavior, confirm handling, and what is preserved, but it explicitly says the operation is destructive while annotations declare destructiveHint=false. That is a direct contradiction in a safety-relevant field.

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?

The description is dense but front-loaded: effects, exclusions, undoability, confirmation behavior, and snapshot source each appear in a purposeful sentence with no filler.

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?

Given that an output schema exists and the schema fully documents parameters, the description covers the remaining agent-critical context: restoration scope, preserved state, undo behavior, confirmation handling, and snapshot selection.

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 baseline is 3, but the description adds useful meaning: confirm enables the dry-run/approval workflow when absent, and snapshotId is sourced from list_catalog_snapshots, with a specific rule for finding the pre-assistant state.

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 and resource: putting a catalog back to a restore point from list_catalog_snapshots. It also names exactly which catalog aspects are restored (pages, products, design, settings), making it distinguishable from edit_catalog and update_catalog.

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?

Clearly directs the agent to obtain snapshotId from list_catalog_snapshots and explains that the newest reason="assistant" point is the state before the last assistant change. It also specifies the confirm: true approval flow, though it does not explicitly compare when to use restore versus selective edit_catalog actions.

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