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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context: snapshots are captured FIRST on every file write, edit, download and shell command, which is why overwritten pages are recoverable. It also discloses pagination behavior (offset/next_offset, byte_offset/next_byte_offset) and the newest-first ordering — real behavioral detail 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?

Front-loaded with purpose, then usage trigger, then return shape and the read-only mode. Dense and mostly waste-free, though the return-shape and paging sentences are long enough that it runs slightly long for a listing tool.

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 an 8-parameter tool with no schema descriptions, the description covers the important modes and paging contract, and an output schema exists so return values need not be restated. It is nearly complete, but omits meaning for site, server, and limit, which an agent would have to infer.

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 0%, so the description carries the burden and largely succeeds: it explains version_id + path for file-history mode, the show=content vs show=diff semantics, and the offset/byte_offset paging contract. However, three of the eight parameters (site, server, limit) are never explained, leaving a gap the schema does not fill.

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 ('Lists automatic version snapshots of the website') with clear scope, and distinguishes itself from siblings by naming site_restore as the follow-up action and by clarifying it is read-only file history. An agent can tell it apart from site_read_file and site_restore without opening a 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?

Explicit trigger conditions are given ('when the user says a change disappeared, was reverted or came back wrong') plus the workflow alternative: find the snapshot, then call site_restore. It also carves out a distinct read-only mode (pass version_id + path with show=content/diff) that explicitly does not restore anything.

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