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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds value beyond that by disclosing the content of the response (change kinds) and framing it as a history feed, though it omits ordering, default window, and whether history is complete or truncated.

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 short sentences, front-loaded with the return payload, then purpose, then the companion tool. Nothing is redundant with the title, which only says 'edit history'.

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?

With no output schema, the description carries the burden of describing returns, and it does so adequately via the change-type enumeration. Minor gaps remain: result ordering, pagination behavior, and how variation_index scopes the history are not hinted at.

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 four parameters (including the unusual user_goal telemetry field and variation_index) are documented in the schema itself. The description adds no parameter-level meaning, so the baseline of 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 and resource ('Return the version history of a site') and enumerates the payload fields (what changed, when, change kind), then names the change-type taxonomy (generation, refinement, content edit, restore). This is distinguishable from siblings like list_variations or get_site without opening any schema.

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?

Gives two concrete use cases — locating a rollback point and narrating site history to a user — and points at the follow-up tool ('Pair with restore_version'). It does not, however, state when to use this versus list_variations, which is the closest sibling and is left unaddressed.

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