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 structurally. The description adds real value on top: it specifies exactly what is restored (the values replaced by a batch) and the 90-day retention limit, which is the key constraint an agent must know before invoking. It does not say what happens when the window has passed or if the batch was already undone, so it is not a 5.

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?

Two compact sentences with zero filler; the action and its scope lead, and the batch-id sourcing follows. Every clause earns its place.

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 tool with no output schema, the description covers the essential facts: what is restored, that it derives from a prior batch, and the 90-day retention window. It leaves unaddressed edge behavior (expired or repeated undo, permissions, reversibility of the undo itself), which is a minor but real gap.

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 including their optionality conditions are already documented in the schema. The description's note that batch comes from seo_fields_apply or seo_fields_history largely duplicates the schema's own batch description ('the batch id from apply or history') and adds nothing about site or server. Baseline 3 is appropriate.

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 (put back) and resource (values a seo_fields_apply batch replaced), and names the sibling tools that produce the values being reverted (seo_fields_apply, seo_fields_history). An agent can distinguish this from seo_fields_apply, seo_fields_history and seo_fields_list 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?

The description gives clear context for use: it reverts a prior apply batch, and the parenthetical '(kept 90 days)' communicates an implicit expiry window. It also tells the agent where the required batch id comes from. It does not explicitly state when NOT to use it (e.g. expired batches, already-undone batches) or name alternative undo tools, so it falls short of the top band.

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