undo_split_composition_event

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

With no annotations provided, the description carries the full burden and does an excellent job: it labels the operation as 'Mutating', explains persistence across models, details the 409 refusal with a structured block when state evolves, and lists the success effects (restore ancestor, tombstone copies, emit `split_undone` event). This is thorough and actionable without contradicting any annotations.

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 dense but well-structured: a one-sentence summary followed by a compact explanation of behavior and side effects. Every sentence adds meaningful information, and the front-loaded 'Mutating' immediately sets the correct expectation. No filler or 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?

Given the tool's complexity (multi-model mutation, refusal conditions) and absence of annotations, the description is remarkably complete. It covers the precondition check, the error case, the exact mutation steps, and the emitted event. An output schema exists, so return-value details are not required, and the description sufficiently explains the tool's behavior for an agent to decide and 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?

The schema provides good descriptions for `model_id` and `split_id`, which cover 67% of parameters. However, `server_version` has no description in the schema, and the tool description does not explain its purpose or semantics either. The description adds little new parameter meaning beyond what the schema already provides, so this is a minimum viable score.

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 applies the inverse of a previous `split_applied` composition event, using a specific verb and resource. It also distinguishes itself from the sibling `undo_lift_composition_event` by noting it is the mirror for splits, making its purpose unambiguous.

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 gives clear context: use this to undo a split event, and notes it is the split counterpart to `undo_lift_composition_event`. However, it does not explicitly mention when not to use it or point to `preview_undo_split_composition` for a non-mutating preview, so it falls short of a 5.

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