Undo

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

The description goes far beyond annotations by disclosing backend-specific behavior (COM vs headless), performance costs (37x slowdown), configuration requirements (EZDXF_UNDO_DEPTH), and redo-branch semantics. No contradiction with idempotentHint or destructiveHint.

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?

Every sentence earns its place: purpose, backend detail, performance cost, alternative, and redo semantics. The structure is logical, front-loaded with the core function, and efficiently dense without being verbose.

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 (backend differences, configuration, performance trade-offs), the description is remarkably complete. It covers behavior, setup, alternatives, and edge cases like redo discard. An output schema exists, so return values need not be explained.

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 tool has zero parameters, so the description need not explain parameter syntax. The schema coverage is 100% (empty). The description implicitly confirms no arguments are needed, which is appropriate; baseline for 0 params is 4.

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 'Undo the last drawing operation' with a specific verb and resource. It distinguishes itself from related operations like drawing_redo and transaction_rollback by explaining exactly what it does and contrasting with alternatives.

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?

Explicitly provides when-to-use guidance: mentions backend differences, default history off, and the need to set EZDXF_UNDO_DEPTH. It also names transaction_begin/transaction_rollback as a cheaper alternative for single checkpoints, giving clear usage context.

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