Undo last change

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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false). The description adds two non-obvious behavioral facts: only values/formulas are restored, not formatting or structure, and the history is in-memory and lost on server restart. That durability caveat is exactly the kind of context annotations cannot carry.

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?

Two tight sentences, front-loaded with the action and its scope, with the caveat parenthesized where it belongs. No filler.

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?

For a no-output-schema tool this covers scope and durability well. It omits only edge behavior such as what happens when there is no history to undo, or how many steps are retained, which are minor for selection and invocation.

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 100% for both parameters, so the schema already explains account and spreadsheet resolution. The description adds nothing parameter-specific (e.g., whether the undo is scoped per-spreadsheet or per-session), so the baseline 3 applies.

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?

Specific verb (undo) plus the exact set of operations it reverses (write_range, append_rows, clear_range), which maps directly onto named sibling tools. An agent can distinguish this from every sibling without opening a schema.

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 scopes usage to writes made 'through this server' and implicitly excludes formatting/structure changes from being undoable, which is meaningful when-to-use context. It stops short of explicitly saying when to prefer it (e.g., immediately after a mistaken write, or that no redo exists).

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