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

Annotations already declare destructiveHint=true and idempotentHint=true, so the risk profile is covered. The description adds real value beyond that by describing the effect (existing baseline is replaced by this run's structure) and by naming the undo path, which is precisely the context an agent needs before performing a destructive, idempotent rebaseline.

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 dense sentence that front-loads the situation (a monitored layout change) before the action and its two scope modes. Every clause carries information; nothing is padding.

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 mutation with no output schema, the description plus annotations cover the essentials: what is mutated, the scope options, and how to reverse it. It stops short of stating permission requirements or whether adopting a baseline affects subsequent run comparisons, which keeps it from a 5.

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 all three parameters are already documented in the schema, including the get_run metrics.pages[].pageKey hint. The description only restates the pageKey-vs-all:true targeting modes without adding format, default, or precedence detail (e.g., what happens if both are supplied), so the baseline 3 applies.

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+resource: adopting a run's detected structure as the new baseline, with the scope switch made explicit (single pageKey vs all changed pages on the run). It also names undo_structure_review as the inverse operation, letting an agent place it correctly among the ignore/undo siblings.

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 opening clause supplies the trigger condition — the monitor found a layout change that was intentional — which tells the agent when this tool is appropriate. It names the undo alternative, but never states the opposite case (e.g., use ignore_structure_change when the change was not intended), so the routing guidance is clear but not exhaustive.

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