undo_split_composition_event

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

No annotations exist, so description carries full burden. It details preconditions (divergence check), failure mode (409 with structured block), postconditions (restore ancestor, tombstone duplicates, persist across models, emit event), and the full lifecycle, providing excellent transparency for an agent.

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?

Two paragraphs with front-loaded intent and code references; every sentence adds value. Slightly verbose for a tool description but remains efficient and well-structured.

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 existence of an output schema (return values not needed), the description covers all behavioral aspects: pre-checks, failure scenarios, side effects, and persistence. No gaps identified for safe agent invocation.

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?

With 67% schema description coverage, the description adds significant value beyond schema for two of three parameters: explains `model_id` must match event's `threat_model_id`, and clarifies `split_id` can be either the event surrogate id or payload split_id. `server_version` is left undocumented.

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?

Description clearly states it applies the inverse of a previous `split_applied` event, distinguishing it from the sibling `undo_lift_composition_event` by explicitly calling out the mirror relationship. The verb 'undo' with the resource 'split composition event' is specific and 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?

Description implies usage for undoing splits and mentions the divergence detector refusal when state has evolved, but does not provide explicit when-to-use vs. when-not-to-use guidance or name alternatives like `preview_undo_split_composition` as a safer first step.

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