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

Annotations already flag destructive/idempotent/non-read-only, and the description adds substantial context beyond them: fields changed by others are preserved and listed in effects.stale, later-touching changes block a full revert, effects lists truncate at 20 with a <name>Count, and the exact failure reasons (already_reverted, stale, nothing_to_revert, not_found, bad_request) are enumerated.

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 purpose is front-loaded in the first clause and nearly every sentence carries distinct operational information. It is a single dense block of text, though, and the long parenthetical error-reason enumeration could be tightened or split for scanability.

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?

With no output schema, the description carries the return contract itself — reverted: false plus reason, revertedBy with batchId and seq, summary counts, and effects.stale keys (changed, missing, would_cascade). Nothing an agent needs to call it or interpret the result is missing.

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% (batchId has no description), and the description fully compensates: batchId is the case-sensitive mcp:… value a write returned, and an id absent from this diagram's change log returns not_found with details.reason "batch". diagramId is covered by 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 (undoes) and a precisely scoped resource (one agent change, identified by a batchId produced by apply_ops or compose_diagram, within 7 days). It names the producing siblings explicitly, so an agent can distinguish revert from apply_ops/compose_diagram without opening schemas.

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?

Explicit about when it works and when it does not: only changes this app made, not manual edits or other apps' changes, only within 7 days, and only for the acting user unless that user is an org owner/admin. It also states the ordering constraint that a series reverts fully only newest-first, which is a real usage rule an agent must follow.

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