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

Annotations already flag destructiveHint and idempotentHint, but the description adds the crucial conditional-guard behavior: the revert only applies while the record still holds what was written, so newer work is never overwritten. It also discloses that new records cannot be undone and that nothing is deleted, which materially shapes agent expectations.

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?

Four compact sentences, zero redundancy, and the trigger condition is front-loaded before the behavioral caveats and the sibling exclusion. The 'AI Agents (inside one system)' scoping prefix reads slightly awkwardly but still earns its place as a caller constraint.

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?

Output schema exists so return values need no explanation, and the single parameter is fully documented. What remains — safety guard, irreversibility of new records, confirmation requirement, and alternative tool for automations — is all present, leaving no gap an agent would need to guess at.

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 change_id description already names its sources (apply_proposal, list_changes), so the schema carries the parameter burden. The tool description adds only the implicit notion of a 'change' being the unit of undo; it contributes nothing beyond baseline for this single parameter.

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 — undo a change the assistant made — and immediately qualifies scope ('values from before back'). It is clearly distinguishable from sibling mutations like set_automation_status or apply_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?

Gives explicit when-to-use ('when the customer asks to undo a change the assistant made'), explicit when-not with the named alternative ('Not for stopping an automation (use set_automation_status)'), and a procedural prerequisite ('Ask the customer before calling it').

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