undo

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description does add real value by disclosing that it can revert a human edit and only the latest combined entry, but it omits what happens on revision mismatch, whether the undo is reversible, and any concurrency/permission expectations for a destructive 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; the verb and scope come first. It is slightly under-specified rather than bloated, but there is no wasted wording.

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 three fully undocumented required parameters and no output schema, the description is too thin. It leaves the agent without the meaning of `expected_revision`, the granularity of a 'combined history entry', or the outcome of a failed 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?

Schema description coverage is 0% across three required parameters, so the description must compensate and largely does not. It never mentions `browser_session_id`, `map_session_id`, or `expected_revision` — the last of which is clearly a concurrency guard the agent needs to understand. 'Latest' vaguely gestures at revision semantics but gives no syntax or failure behavior.

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 and resource: undoes the editor's latest combined history entry. It is distinguishable from the sibling `redo`, but the phrase 'combined history entry' is jargon that leaves the exact unit of reversal ambiguous. The clarifying clause 'including a human edit' hints at scope without fully defining it.

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?

Implied usage (revert the most recent edit) is apparent, but there is no explicit when-to-use/when-not guidance and no mention of the obvious alternative `redo`. Nothing tells the agent how this behaves relative to state-reading siblings like `get_state`.

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