undo_last

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

No annotations exist, so the description carries the full burden and does so: it explains that each step is reversed exactly (commit removed, edit restored verbatim, delete re-inserted in place, arrays and waste/multiplier pairs restored whole), that reads are never journaled so n counts mutations not calls, and how load_plan interacts with the history.

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?

Front-loaded with the action, and nearly every clause is load-bearing (reversal fidelity, journaling rule, scope caveat). The mid-sentence enumeration of reversal semantics is dense but informative rather than repetitive, so the length is justified with only minor tightening possible.

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 one-parameter mutation-reversal tool with no annotations, the description supplies everything an agent needs: what is reversible, how precisely, the counting rule, scope limits, and interaction with load_plan. The output schema covers return values, so nothing material is 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?

Schema coverage is 100% and the single n parameter is documented in-schema, so the baseline is 3. The description earns an extra point by clarifying that n counts state-changing gestures rather than tool calls made, which is a semantic distinction the schema's '1–100 steps' wording does not capture.

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?

States a specific verb (undo) and resource (last n mutations) and enumerates exactly which gestures count: measure_polygon commits, edit_shape, delete_shape, edit_materials, edit_condition, and RFI verbs. An agent can distinguish this from delete_shape or the RFI delete siblings without opening another 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?

Gives concrete triggering scenarios (a sweep committed against the wrong condition, a batch on the wrong sheet) and states the payoff (one call instead of N deletes). It also draws explicit boundaries: session history only, not the browser canvas undo stack, and cleared by load_plan.

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