undo_change

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

The description adds real behavior beyond the annotations: undo applies to the latest change by anyone, not just the caller's own, and redo=True reapplies it. That pair of facts materially shapes how an agent should use the tool. It does not disclose failure behavior (no-op case), whether undo is scoped per case, or whether history is truncated after undo — gaps that annotations (readOnly=false, destructive=false, idempotent=false) do not fill in.

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 short sentences, zero filler, with the primary action front-loaded and the optional flag explained second. Nothing is redundant with the title or schema.

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 mutation tool with no output schema, the description usefully says it reports what was undone, which covers the return value. However, with three undocumented parameters and no output schema, the missing case scoping, language behavior, and no-op handling leave the definition short of what an agent needs to call it confidently.

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 description coverage is 0%, so the description carries the full burden, yet it explains only the optional 'redo' flag. The required 'case_id' and the 'language' enum are never mentioned, leaving an agent to guess what the case scoping means when the description says the undo targets changes by 'anyone'.

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 names a concrete verb and resource ('Undo the latest change') and adds a valuable scope qualifier: the change may belong to 'anyone (person or AI)'. It also explains the redo flag's effect, so an agent can distinguish this from sibling mutation tools like update_case or clone_case. It stops short of 5 because 'change' is never grounded in a case context, even though case_id is required.

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?

Usage is only implied: an agent must infer that this is called after a change was made and should be reverted. There is no statement about what happens when no change exists to undo, no prerequisite check, and no pointer to any alternative recovery path among the many case-management siblings.

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