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

Annotations already declare readOnly/idempotent/non-destructive, so "changes nothing" is largely redundant, but "Free" adds a cost trait annotations don't cover. The pagination behavior (one page, next_cursor emitted when more exist) is genuine behavioral context beyond the 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 short clauses, front-loaded with what the tool returns, then pagination mechanics, then the dependency. No filler and nothing buried.

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 return-shape burden and does describe the page envelope and cursor. It does not say what fields a version entry exposes (id, timestamp, label), which matters because an agent must extract a version id for soclo_page_restore.

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 coverage is 100%, so the baseline is 3; the description earns an extra point by explaining the cursor round-trip — that the value to pass as `cursor` is the `next_cursor` from the prior response. `limit` is left entirely to the schema, but its meaning is unambiguous.

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+resource ("List saved versions of the website") with ordering ("newest first") and scope ("one page of history"). It implicitly separates itself from soclo_page_restore by naming it as a downstream consumer, but doesn't distinguish itself from the closer confusables soclo_page_get or soclo_page_pages.

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?

"soclo_page_restore needs a version id from here" gives a concrete call-this-first workflow, and "Free; changes nothing" signals safe invocation. It stops short of stating exclusions — e.g., use soclo_page_get for current page content rather than history.

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