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

Beyond the destructiveHint=true annotation, the description discloses the 30-day restore window, that the reviewed preview is applied exactly, that a changed record is refused, idempotency/retry behavior via request_id, the $0.10 cost, and API-key auth requirement. This is unusually rich behavioral context.

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 two key constraints ('Preview first, 30-day undo'), but the preview_destructive_change call and its arguments are described almost twice, which is redundant. Still, every section carries useful 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?

For a destructive, multi-step, costed operation, the description covers the full lifecycle (preview, confirm, apply, restore) plus auth and pricing, and an output schema exists to carry return values like restore_id. Nothing critical is missing.

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?

With 67% schema coverage, the schema already documents preview_id, request_id, and restore_window_acknowledged. The description reinforces these (preview_id must come from preview_destructive_change, restore_window_acknowledged must be true after review) and references canonical_id/retired_ids through the preview-call example, adding meaning but not fully covering every parameter.

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 ('merge moments') and specifies the exact effect: conflicting story, date, place or event links stop the merge, and people/tags/media are unioned. This is enough for an agent to distinguish it from siblings like merge_people, update_moment, or delete_moment.

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?

The description gives a clear mandatory workflow: preview via preview_destructive_change first, obtain user confirmation, then call with preview_id and restore_window_acknowledged. It does not explicitly compare against alternative merge/dedup siblings, but the when-to-use flow is unambiguous.

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