preview_undo_split_composition

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

The description explicitly states that the tool does not mutate state, which is critical behavioral information not available from annotations (none provided). It also describes the output shape ({plan, refusal}) and the specific inverse operations. Without annotations, this carries the full burden and does so well, though it could add prerequisites or permissions.

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 two concise sentences plus a clarifying line about the counterpart. It is front-loaded with the key purpose and zero waste. Every sentence serves a purpose.

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 the presence of an output schema (not shown but noted), the description does not need to detail return values. It explains the purpose, the counterpart, the non-mutating behavior, and the output shape, which is sufficient for an agent to select and invoke 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?

Schema coverage is 67% (model_id and split_id have descriptions; server_version does not). The description adds contextual meaning beyond the schema by clarifying the split_id parameter can be a surrogate id or a structured id, and that model_id must match the event's threat_model_id. This adds value beyond the baseline of 3.

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: to preview the inverse plan for a prior split_applied event without mutating state. It uses a specific verb (preview) and resource (inverse plan), and distinguishes itself from its sibling preview_undo_lift_composition.

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 context on when to use this tool (to preview an undo plan before executing) and explicitly mentions the counterpart tool for lifts. However, it doesn't include explicit when-not-to-use instructions or alternative tools beyond the counterpart.

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