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

Goes well beyond the annotations: first publish starts a $5/month rent, later publishes cost $0.01, failed publishes cost nothing, and the last 20 versions are retained. That combination of billing consequence and version retention is exactly the context an agent needs before a mutation it cannot undo by itself. Nothing here contradicts readOnlyHint=false / destructiveHint=false.

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?

The opening clause is well front-loaded, but the pricing is stated twice — first as "$5 a month from the balance" / "later publishes cost $0.01", then again as "Costs $5 for the first publish... $0.01 after that ($5.00 the first time, then $0.01; at most $5.00 a call)". That redundancy is noise an agent must parse through.

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 single-parameter mutation with no output schema, it covers everything that matters: the visible effect, the cost model including the failure case, and the recoverable history window with a pointer to the rollback tool. Nothing needed to call it safely is missing.

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?

There is only one parameter and the schema already documents it at 100% coverage ("The site's name, as in cncto.co/w/<name>"). The description reinforces the same URL-shape meaning but adds no new constraint (length limits, naming rules) beyond the schema, so a 4 rather than a 5.

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?

"Put the draft online at cncto.co/w/<name>" names a specific verb (publish) and the exact resource (this site's draft at a public URL), and the phrase "until the next publish" separates it cleanly from website_preview, website_unpublish and website_rollback. An agent can select it 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?

It gives clear context (the publish makes the current draft live for visitors, superseding the previous version) and points to website_rollback for restoring history. It never states the inverse conditions — e.g. that previewing must happen first, or that this is the wrong tool when the site should stay private (website_unpublish) — so the exclusion side is only implied.

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