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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true), so the bar is lower. The description adds genuine value by scoping the operation to the single most recent decision ('the last accept or ignore') and to one page, telling the agent it is a one-step, non-stacking undo.

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 sentence, zero filler, and the object of the undo is front-loaded before the scope qualifier.

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 two-parameter mutation with no output schema but full annotation coverage, the description gives enough to invoke it, but omits what state is restored, what happens if there is nothing to undo, and how results are surfaced.

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 100%, so baseline is 3. The schema descriptions ('The run', 'The page') are terse, and the description adds no format, id, or lookup detail for runId/pageKey.

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?

Specific verb (undo) plus the exact object being undone (the last accept or ignore). The phrase 'structure monitor' distinguishes it from the sibling undo_visual_review, which handles a parallel but different review surface.

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?

Usage is implied rather than stated: an agent can infer it is called after a structure accept/ignore to reverse it, but the description names no alternatives or preconditions (e.g. what happens if there is no prior decision).

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