undo

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

Annotations declare readOnlyHint=false, and "undo" is consistent with a mutating operation, so there is no contradiction. However, the description adds nothing beyond that: it does not say what state is restored, whether the undone transaction can be redone, what happens when the undo stack is empty, or whether sessionId scopes the operation.

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?

A single front-loaded sentence with no filler, which is structurally clean. The terseness is arguably under-specification rather than over-wording, but nothing in it is wasted.

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 mutating tool with three undocumented optional parameters, no output schema, and only minimal annotations, the description is far too thin. It does not explain idempotency, concurrency via expectedRevision, session targeting, or failure behavior when there is nothing to undo.

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?

All three parameters (requestId, sessionId, expectedRevision) have 0% schema description coverage, so the description carries the full burden and supplies no meaning for any of them. The interaction between sessionId scoping, requestId idempotency, and expectedRevision concurrency is completely undocumented.

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?

"Undo one editor transaction" gives a specific verb (undo) and a scoped resource (one editor transaction), and the granularity wording separates it from the sibling redo tool. It stops short of naming that sibling or stating which editor/session context is affected, so it is clear but not fully differentiating.

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 contains no when-to-use guidance, no mention of the redo sibling as the inverse operation, and no preconditions such as needing an active session or an undoable transaction. An agent must infer everything about selection from the name alone.

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