Undo a completed batch

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

Adds real context beyond the annotations: repeat calls return the existing operation (corroborating idempotentHint=true), conflicting messages are surfaced rather than overwritten, and indeterminate states are never guessed. That is genuinely useful safety behavior. The gap is that it never explains what the `confirm` flag gates, so the agent cannot tell whether an unconfirmed call performs or merely plans the undo.

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 short sentences, no filler, each carrying a distinct fact (scope, conflict rule, unknown-state rule, idempotency). Front-loaded with the precondition before the edge cases.

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?

An output schema exists, so return values need no explanation, and the conflict/idempotency semantics are well covered. But for a 0%-coverage two-parameter mutation, leaving `confirm` entirely undocumented is a meaningful hole that could cause wrong invocation.

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% and neither parameter is mentioned in the description. The `confirm` boolean defaulting to false is behaviorally critical — an agent that omits it may get a dry-run or no-op — yet its purpose is documented nowhere. `operation_id` is at least inferable from "batch" context, but not from the text.

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 confirmed batch changes") plus a precondition ("whose touched fields have not changed again"), which is far more precise than the title's tautology. It does not name its closest siblings (mail_batch_preview, mail_batch_apply), so the agent must infer that this is the third step in that workflow.

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?

"Undo confirmed batch changes" implies the precondition that mail_batch_apply already ran, and the conflict rule ("Messages changed by someone else are reported as conflicts") tells the agent what will and won't be reverted. There is no explicit exclusion or pointer to an alternative, so the routing is clear but not fully complete.

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