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

Annotations already declare destructiveHint=true, and the description adds substantial behavioral detail: what gets discarded (the change and everything later), how preview works before applying, and that a follow-up undo restores the previously discarded changes. It also notes that changes can come from tool calls or courtside page entries, providing context beyond the annotations. This richly informs the agent about consequences and state transitions.

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 concise yet comprehensive, with a clear structure: overview sentence, conditional behavior for the two modes, preview/confirm explanation, and the redo follow-up note. Every sentence earns its place, and the information is front-loaded, making it easy for an agent to parse quickly.

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?

The tool is complex with multiple modes, a preview mechanism, and a redo behavior. The description covers all these aspects and provides necessary context about change tracking origins. It references get_audit_log for obtaining change IDs, which integrates well with sibling tools. Given the rich output schema and annotations, the description is complete enough for the agent to use the tool correctly.

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?

The input schema already provides 100% parameter coverage with clear descriptions. The description reinforces the semantics of to_change_id and confirm but does not add significant new meaning beyond what the schema states. Since schema coverage is high, a baseline of 3 is appropriate; the description adds minimal extra value for parameter understanding.

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's purpose with a specific verb ('Roll the tournament back') and identifies the resource (tournament state). It distinguishes between two modes (undo latest vs. undo to a specific change), which differentiates it from any potential sibling tools. The reference to get_audit_log for obtaining change IDs further clarifies its role within the toolset.

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 provides clear usage context: when to omit to_change_id (undo most recent change) and when to include it (undo a burst of unwanted changes). It also explains the preview/confirm flow and the redo behavior. While it doesn't explicitly list alternative tools, the conditions for use are well-defined and sufficient for the agent to decide when to invoke this tool.

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