preview_undo_split_composition

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

With no annotations provided, the description fully carries the behavioral disclosure. It explicitly states no state mutation, labels itself read-only, and explains the output shape ({plan, refusal}) and the plan's split-specific content (restore at ancestor, tombstone duplicates). This is comprehensive for a read-only preview tool.

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 and front-loaded, with the core purpose and read-only nature stated first. The second sentence adds useful sibling context and output shape details, and every sentence contributes meaning without redundancy.

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 description adequately covers the tool's purpose, read-only behavior, output shape, and relationship to sibling tools. Given that an output schema exists, it does not need to detail return values, making the description complete for its complexity.

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 schema already provides descriptions for model_id and split_id, which the description does not further elaborate. The description adds no new parameter-level meaning beyond what the schema states, so the baseline 3 for 67% schema coverage 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?

The description explicitly states the tool's purpose: preview the inverse plan or divergence refusal for a prior split_applied event, and clearly identifies it as read-only. It distinguishes itself from the sibling preview_undo_lift_composition by noting the split-specific inverse operations.

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 indicates this tool is the counterpart to preview_undo_lift_composition for splits, implying when it should be used. It clearly signals that it is a preview (read-only) and not the applying operation, but does not explicitly mention exclusions or alternative tools like undo_split_composition_event.

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