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

Annotations already flag destructiveHint=true, but the description goes further by quantifying the blast radius (every change since the target) and disclosing reversibility ('The undo is itself a change, so it can be undone too'). That reversibility detail is exactly the extra context an agent cannot infer from structured fields.

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?

Three tight sentences with zero padding; the destructive cascade is front-loaded before the provenance and reversibility notes.

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, output-schema-less tool, the description covers scope, input provenance, and reversibility, and annotations carry the safety profile. It does not mention confirmation requirements or that the token may come from the Authorization header, though the schema handles the token.

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 both parameters are already documented, and the description's 'Take the change id from history' largely restates the schema's own 'From history' for change_id. It adds only a mild cross-tool pointer, not new semantics, 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 (undo/put back) and resource (the site, to its pre-change state) and precisely delineates the scope: the named change plus every change after it. It is clearly distinguishable from siblings like history (which supplies the change id) and write_site.

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?

'Take the change id from history' gives a concrete prerequisite and routes the agent to the sibling that produces the input. It does not, however, state when to prefer undo over other mutation paths or any exclusions, so it stops short of full when/when-not guidance.

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