undo_last_edit

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

Annotations already declare the tool destructive and not read-only. The description adds valuable context by clarifying the operation is in-memory only and does not affect disk state, which is not captured by the annotations. However, it does not disclose behavior when there is no edit to undo or how expected_revision affects the operation.

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 a single sentence, front-loaded with the action, and contains no filler or redundant phrasing. Every word adds meaning.

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 core behavior and the important in-memory/disk distinction, and an output schema exists. However, it omits the meaning of expected_revision and does not address edge cases like undoing when no edit exists, leaving the tool partially underspecified for a destructive operation.

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 description coverage is 0%, so the description carries the burden of explaining parameters, but it mentions neither project_id nor expected_revision. The parameter names are somewhat self-explanatory, but the optional expected_revision's role as a concurrency guard is completely 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?

The description uses a specific verb ('Undo') with a clear resource ('the last in-memory edit') and a key scoping qualifier ('without touching disk'). This clearly distinguishes the tool from siblings like redo_last_edit and other edit operations.

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 implies when to use the tool—when you need to revert the most recent in-memory change without persisting—but it does not explicitly state when not to use it or mention alternatives such as redo_last_edit. The usage context is clear enough, but exclusion guidance is absent.

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