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

Goes far beyond the destructiveHint annotation by detailing idempotency, state transitions (CP1/CP2), cleared fields, the confirm_discard flow, and the financial consequence of discarding paid-for drafts. This richly discloses behavior not otherwise visible.

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 well-organized and front-loaded with the purpose. Each paragraph adds unique value: usage context, parameter behavior, idempotency, and safety. No fluff or repetition; every sentence earns its place.

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 destructive tool with no output schema, the description covers all essential aspects: what triggers use, exact state changes, idempotent behavior, the confirmation safety mechanism, and credit implications. It leaves no critical gaps for an agent to safely invoke it.

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 only 33% (only acknowledge_discard has a description). The description compensates by explaining the 'to' parameter's two values (story/angle) and their distinct effects, plus clarifies acknowledge_discard's necessity and consequence. session_id is self-evident.

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 clearly states the tool reverts a session to an earlier checkpoint, with specific verbs and resources. It distinguishes itself from siblings like niche_session_cancel by focusing on checkpoint reversion without starting a new scan, and elaborates on the two target checkpoints (story/angle).

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 states when to use: when the picked story/angle isn't right and you want to re-pick 'without starting a new scan.' It also covers exclusions and caution around reverting finished runs, providing clear context for safe use.

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