undo_last

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

The annotations declare readOnlyHint=true, but undoing is a state-mutating operation that rewinds the scene and history. The description only mentions undo semantics and does not disclose side effects such as history consumption or failure when there is no operation to undo. This directly contradicts the read-only annotation.

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, stating purpose and equivalence in two short sentences. The English sentence repeats the Chinese content exactly, so it is not perfectly information-dense, but it remains concise and readable.

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 tool is simple, has one optional parameter, and the schema fully documents 'steps', so the description is enough to select and invoke the tool. However, there is no output/return expectation or failure behavior for an empty undo stack, and the contradictory annotation undermines the completeness of the overall context.

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?

Schema coverage is 100% and the only parameter 'steps' already has a description including the default value. The description maps 'last N' to that parameter but adds no syntax or behavioral detail beyond 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 uses a specific verb and object ('Undo the last operation (or the last N)') and grounds it in a familiar equivalent, Ctrl+Z in Max. It clearly conveys the undo semantics and is distinguishable from the sibling redo_last by naming the reverse action.

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 establishes clear context: use it when a user wants to undo recent scene changes, equivalent to pressing Ctrl+Z. It does not explicitly state when not to use it or point to alternatives like redo_last, 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.