preview_undo_lift_composition

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

No annotations are provided, so the description carries full burden. It explicitly states 'WITHOUT mutating any state' and 'Read-only counterpart', clearly indicating no side effects. It also describes what the preview returns: either the inverse state operations or the reasons for divergence refusal. This provides good behavioral transparency beyond the basic read-only nature.

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 paragraphs of moderate length. The core purpose is front-loaded in the first sentence. Every sentence provides meaningful information without fluff. It is slightly longer than necessary but still 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 presence of an output schema (context signals indicate yes), the description explains the context of the confirmation flow and what the preview contains (inverse operations or divergence reasons). With 3 parameters and no nested objects, the description covers the key aspects. However, it could be more explicit about the return format, but the output schema likely handles that. Overall, it is fairly complete.

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 descriptions cover 2 of 3 parameters (lift_id, model_id) with detailed explanation. However, the server_version parameter lacks any description in both schema and tool description. The tool description does not add parameter-level information beyond what is in the schema. Since schema coverage is 67% (incomplete), the description should compensate for the missing parameter info but does not. Thus, it adds minimal value over the schema.

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 verb 'preview' and the resource 'inverse plan (or divergence refusal)' for a prior lift_applied event. It specifies it is a read-only counterpart to undo_lift_composition_event, distinguishing it from its sibling. This provides specific verb+resource and sibling differentiation.

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 states it is used by the confirmation flow so the operator sees what an undo would do before committing. It identifies itself as a read-only counterpart to undo_lift_composition_event, providing clear context for when to use it (before an undo) and implicitly when not to use it (for actual undo). However, it does not explicitly exclude other alternatives.

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