undo

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

The description adds meaningful behavioral context beyond the annotations by stating that it restores 'exact previous values' and limits itself to this assistant's change groups. This complements the readOnlyHint=false annotation by confirming this is a mutation while also suggesting non-destructive restoration behavior.

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 entire description is one tight sentence with a clarifying parenthetical. The key action, scope, and behavioral nuance are front-loaded with no wasted words.

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 purpose, scope, and outcome, which is enough for a simple default invocation. However, it leaves the 'steps' parameter semantically ambiguous and provides no information about response behavior or failure cases, so it is not fully complete for confident multi-step use.

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?

The only parameter, 'steps', is not explained in the description, and schema description coverage is 0%. The plural 'group(s)' hints that multiple groups can be reverted, but the description never explicitly maps 'steps' to a number of change groups or clarifies valid values.

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 ('Revert') and a specific resource ('last change group(s) made through this assistant'), clearly distinguishing this from generic undo or other sibling tools. The parenthetical ('restores the exact previous values') adds precise semantics that help an agent understand the expected outcome.

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 phrase 'made through this assistant' provides a clear scope: this tool applies to assistant-originated changes and implicitly not to external changes. No alternative tools are named, but the boundary is specific enough for an agent to infer when to invoke it.

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