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

Annotations declare destructiveHint=true and readOnlyHint=false, so the description should clarify what is destroyed. It does not say whether undoing turn N discards all subsequent turns' changes, whether the undo is itself reversible, or whether re-running it steps further back. For a destructive rollback, these are the questions an agent must have answered.

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?

One short sentence with no wasted words, which is structurally clean. The flip side is that the brevity is under-specification rather than efficiency — the single sentence carries no operational detail.

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?

This is a destructive, non-read-only mutation with no output schema and no stated result state. Given the complexity of turn-based rollback, the definition should explain the resulting document state and any irreversibility; neither is present.

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%, so the baseline is 3. The phrase "an earlier turn of the conversation" adds conceptual meaning to the opaque schema note "The turn's number #." by framing turn as a conversational index, but nothing is said about valid ranges, ordering, or what document_id constrains.

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?

"Puts back what an earlier turn of the conversation changed, as it was before" conveys a rollback of a prior turn, but it is largely a restatement of the name deck_undo_turn. It never says which artifacts are restored (slides, styles, images, text) or the scope of a "turn," leaving the agent to guess at the resource impacted.

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?

No guidance on when to use this versus sibling mutation tools such as deck_edit_slide or deck_delete_slide, and no exclusions. Critically, it never explains how an agent determines a valid turn number, which is a required parameter — the caller has to infer the turn model entirely.

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