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

Annotations already flag destructiveHint=true and idempotentHint=true; the description goes well beyond that by disclosing the preview/apply safety gate, that the draft is untouched, that the site can end up offline when no earlier version exists, and that a personal connector token is required. The refusal-handling note ('read out as given') is unusual and genuinely useful context. Nothing conflicts with the annotations.

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 the effect, then the call protocol, then authorization — a sensible ordering with almost no filler. The fallback sentence ('the version published before it goes live again or, when there is none, the site goes offline') is syntactically tangled and needs a second read, which is the only real cost.

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?

A destructive mutation with an output schema, and the description supplies everything the structured fields cannot: preview-then-confirm flow, authorization boundary, draft preservation, and the no-previous-version outcome. An agent has enough to execute correctly on the first attempt.

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 baseline is 3, but the description adds real meaning: `confirm` is not just a boolean but the gate that separates preview from mutation, and `changeId` is tied to a specific previewed change rather than being an arbitrary id. The only gap is that eventIdOrName/siteId semantics come purely from the schema.

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 statement ('Takes back the last publish of one event website'), and the fallback clause ('when there is none, the site goes offline') pins down exactly which state transition is meant. It never names site_publish (the natural inverse sibling) explicitly, so an agent must infer the pairing rather than be routed to it.

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 an explicit two-step protocol: first call without `confirm` yields a preview, the organizer must approve, then call again with `confirm: true` plus the `changeId`. It also states who may call (organizer only, everyone else refused), leaving no ambiguity about preconditions or sequencing.

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