Undo

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

Annotations already declare destructiveHint=true and idempotentHint=false, so safety is covered; the description goes well beyond them by explaining the restore-from-snapshot mechanism, the conflict-detection-and-refusal behavior (including that it lists blocking objects), and a real limitation (minute-rounded edit times make same-minute edits undetectable). That is exactly the kind of behavioral disclosure that cannot be inferred from structured fields.

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 sentences, front-loaded with the core action and default behavior, then escalating to the lookup tool, the refusal semantics, and the edge-case limitation. No filler, no restatement of the title or annotations.

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 destructive, non-idempotent mutation with no output schema and only two params, the description supplies everything an agent needs: default behavior, id acquisition path, refusal conditions, override flag semantics, and a known blind spot. Nothing material is left implicit.

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 only 50% (undo_id has no description), and the description compensates: it defines undo_id as optional with 'no id reverts the most recent change that has not been undone' plus a lookup path, and it defines force by tying it to the conflict refusal rather than merely repeating the schema's terse 'Overwrite edits made after the original change.' Both parameters gain meaning beyond the schema.

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+resource ('Revert a change made through this server') with scope qualifier ('through this server'), which cleanly separates it from siblings that write (notion_update_page, notion_patch_block) and from the read/inspection tools. The default no-id behavior is spelled out, so the agent knows the operation is optional-argument driven.

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?

Explicitly routes the agent to notion_history to obtain ids, defines the no-id fallback, and states the precise when-not condition: the tool refuses if anything it would restore was edited later, unless force is true. That is a complete use/avoid decision rule rather than an implied one.

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