Propose reversing an applied proposal

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

The name 'undo_changes' implies immediate reversal, and the description corrects that misconception head-on: 'Changes nothing by itself: like any proposal, it must be approved and then applied with apply_changes.' It also discloses the concrete semantics of the reversal. This is context annotations cannot supply on their own.

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 sentences, no filler, and the most important fact (it only builds a proposal) is placed immediately after the one-line purpose. Every clause earns its place.

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?

No output schema exists, yet an agent has everything needed: what the tool produces, that it is inert until approved and applied, and the required follow-up call. Nothing material is omitted for a single-parameter tool.

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?

Only one parameter and schema description coverage is 100%; the schema already tells the agent the id comes from change_history or apply_changes. The description adds no additional parameter meaning, so 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?

States a specific verb and resource ('Builds a new proposal that would reverse an applied one') and enumerates the effects (removes negatives, restores statuses and budgets). This clearly separates it from propose_changes, apply_changes, and discard_proposal.

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?

Makes clear it targets an *applied* proposal and names the required follow-up path (approve, then apply_changes), which is exactly the routing an agent needs. It stops short of an explicit exclusion (e.g. use discard_proposal for a pending, un-applied proposal), so it's clear context rather than full when/when-not guidance.

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