undo

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the bar is lowered, yet the description adds a genuinely useful caveat: only native undoable edits are guaranteed, meaning other mutations may not be reverted. It leaves open the failure mode (what happens with an empty undo stack), whether repeated calls walk further back in history, and whether confirm_delete/expected_revision gate a real deletion.

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 the operation and its caveat front-loaded; no filler, no restatement of the name, nothing to trim.

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?

An output schema exists, so return values needn't be explained, and the core semantics of undo are stated. But for a mutating tool wrapped in an argument object containing dry_run and confirm_delete, the description omits the safety-parameter semantics entirely, which is exactly the context an agent needs before invoking it.

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 description coverage is 0%, and the single required parameter is a nested "request" object exposing dry_run, confirm_delete, and expected_revision with no documentation anywhere. The description says nothing about these fields, so an agent cannot infer that dry_run previews the undo or what expected_revision protects against. This is the definition's largest gap.

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?

"Invoke Editor native undo once" gives a specific verb (invoke undo), a specific target (Editor native undo stack), and a scope limit (once). The agent can tell what it does without reading the schema. It stops short of 5 because it doesn't distinguish itself from any state-changing sibling (e.g., batch/snapshot restore paths), leaving the boundary implicit.

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 phrase "once" is an actionable usage constraint — it implies the agent should not loop this tool for multi-step undo, which is real guidance. However, there is no explicit when-not, no prerequisite (e.g., history must exist), and no named alternative for reversing edits that aren't native undoable.

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