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

With annotations already declaring non-read-only, idempotent, non-destructive and closed-world, the description still adds substantive behavior: the optimistic-concurrency contract (stale base_version_id saves nothing and returns the latest version id), that earlier versions are retained, and that no published website changes. Those are exactly the facts an agent needs before firing a mutation.

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?

Four sentences, front-loaded with the outcome, with no filler. The second sentence is long and clause-stacked, but every clause carries distinct file-merge semantics rather than repetition.

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 nested-object mutation with no output schema, the description covers the return value (preview link, or latest version id on conflict), the merge rules, and site-safety. The unnoted 'name' parameter and lack of explicit create_website routing are the only shortfalls.

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 88%, so the baseline is 3; the description earns a bump by explaining the interaction between files, keep_unchanged_files and remove_paths, and by clarifying that business is the alternative payload for starter-layout drafts. The only gap is the 'name' parameter, which neither the schema nor the description explains.

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?

Opens with a specific verb and resource — 'Saves a new version of a private draft and returns a preview link' — which immediately separates it from read-only siblings like get_website or get_preview_link. It does not name create_website as the alternative for producing a new draft, so the differentiation is implicit rather than explicit.

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 concrete conditional guidance inside the call: files replace/add while unsent files are kept, remove_paths deletes, and a starter-layout draft takes business details 'instead of files'. It also tells the agent not to use a stale base_version_id. What's missing is routing to create_website when no draft exists yet.

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