fusion_undo

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

Annotations indicate non-read-only behavior, and the description adds context about preventing a specific design flip, providing useful behavioral insight beyond annotations.

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?

Extremely concise single sentence with a clarifying parenthetical. No redundant information.

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 zero-parameter, no-output-schema tool, the description fully captures the purpose and a key behavioral context, leaving no gaps.

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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter details; it is irrelevant and thus adequate.

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 clearly states the tool undoes the last operation with a verb and resource. The parenthetical adds specificity about guarding against a design flip, which distinguishes it from the sibling fusion_redo.

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 implies usage to undo operations and avoid parametric-to-direct flips, but lacks explicit guidance on when not to use or mention of alternatives like fusion_redo.

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