Preview Undo Composition

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explicitly states 'WITHOUT mutating any state' and 'Read-only,' and describes the return shape as '{plan, refusal}' for both event types. This covers the key behavioral traits an agent needs, though it does not discuss authentication, errors, or rate limits.

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 compact and front-loaded with the most important fact: this is a read-only preview that mutates no state. It then explains the relationship to undo_composition_event, the confirmation-flow use case, and the return shape without redundant or filler sentences. Every sentence earns its place.

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 covers the tool's purpose, its relationship to a sibling tool, its non-mutating behavior, and its return shape enough for an agent to invoke it correctly. The schema supplies detailed parameter semantics and the output schema is present, so the remaining guidance is sufficient. No critical information appears to be missing.

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 input schema already provides detailed descriptions for event_id, model_id, and event_type, so the description does not need to add much parameter-level meaning. The description adds useful background on the plan/refusal result but does not add semantic detail beyond what the schema already provides for the parameters. With 75% schema coverage, the baseline of 3 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 uses a specific verb ('Preview') and resource ('inverse plan ... for a prior composition event') and explicitly says it is read-only. It also names its sibling 'undo_composition_event' and positions itself as the read-only counterpart, which clearly differentiates it from the actual undo operation.

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 usage context: it is used by the confirmation flow so the operator sees what an undo would do before committing. It names the alternative tool (undo_composition_event) and implies when not to use this tool (when actually committing the undo), though it does not explicitly state 'use undo_composition_event instead when ready to commit.'

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