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

The description discloses behavioral traits beyond annotations: that tokens are single-use within a 30-minute window, that different token types have different effects (some delete the created event, some reverse the whole change), and that batchUndoToken removes auto-created events and voids proposals. The destructiveHint=true annotation aligns with the described dedructive effects rather than contradicting them. For a mutation tool with no output schema, the description carries substantive behavioral detail about what each token type does.

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?

The description is dense but front-loaded with the purpose. It uses parentheticals effectively to enumerate token effects. It's somewhat lengthy (a single long paragraph) but every sentence adds meaningful information about token semantics and edge cases. The final clause about alternatives is a useful closing note rather than filler.

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 tool with a single parameter at 100% schema coverage, no nested objects, and no output schema, the description is thorough. It explains the full token-type matrix, the time window constraint, the batchUndoToken special case, and clearly documents the return as per-token `results`. It even gives an alternative approach for a related need. This is essentially complete for the tool's complexity.

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% (the single `tokens` parameter is documented, including the batchUndoToken variant). The description adds valuable semantics beyond the schema by explaining that tokens are time-limited (30-minute window), single-use, and that different token types have distinct effects. It also clarifies the maxItems=20 and minItems=1 constraints implicitly through the 'recent' framing. The description genuinely supplements 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?

The description uses specific verbs (revert, roll back, take back, cancel) tied to a clear resource (recent schedule/confirm_schedule/write_events/delete_events/review_day/manage_backlog operations) via their undo tokens. It explicitly enumerates the source tools and the token requirement, making the scope unambiguous. This distinguishes the tool from siblings like review_day and write_events by focusing on the undo mechanism specifically.

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 clearly states when to use this tool (with a token from a recent call) and gives an explicit 'when-not' with an alternative: 'to discard a whole day's reflection by date instead, use review_day with action 'discard''. It also explains the constraints under which the tool works (within 30 minutes, while tokens remain active), which is essential usage context for an agent.

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