lore_rollback

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

Although annotations already flag destructiveHint=true and idempotentHint=false, the description goes far beyond them: it enumerates what is deleted (world/, characters/, chapters/, summaries/), that in-progress workflows, pending lore_resume runIds and inspection receipts vanish, that later lore_configure/lore_style_anchor changes revert, that archives exist but have no restore tool, and that no model calls occur. This is exceptionally rich behavioral disclosure.

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 long but dense and front-loaded: purpose and usage lead, followed by destructive scope, recovery limitations, and return shape. Every sentence carries decision-relevant information, though the density is near the upper limit.

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 complex, irreversible mutation tool with no output schema, the description covers the trigger condition, prerequisite check, destruction scope, secondary side effects, recoverability limits, and the return shape. Nothing an agent needs to invoke it safely 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?

Schema description coverage is 100%, so the schema already documents workId, chapter, and project. The description's framing of the chapter boundary ('manuscript up to that chapter remains, later ones disappear') largely restates the schema's chapter description, adding little new parameter-level detail. Baseline 3 is appropriate.

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 (rollback/restore) and resource (canon and machine state to a chapter's snapshot) and explicitly distinguishes itself from siblings by naming lore_snapshot_status and lore_sync. An agent can tell exactly what this does versus adjacent tools.

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?

Gives an explicit precondition ('call only when the user has explicitly said to cancel already-committed chapters'), a mandatory first step (check target chapter with lore_snapshot_status), and an alternative for a different case (use lore_sync for manual edits). Nothing is left to inference.

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