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

Annotations already declare destructiveHint=true, so the description's job is to add context beyond that. It does: 'A snapshot of the previous live version is taken first, so it's undoable' explains the mitigating safety mechanism behind the destructive operation. This is genuinely valuable behavioral disclosure, though it doesn't address permissions or post-publish side effects like rebuilds.

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?

Two sentences with zero filler. The primary action is front-loaded in the first sentence, and the second sentence earns its place by adding the snapshot/undo safety detail. Nothing extraneous.

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 low-complexity, single-parameter tool with annotations already covering the destructive profile, the description covers the essentials: the action, the hosted-site scope, and the undo safety net. The main gap is unaddressed slug semantics and the absent return-value note, but given no output schema and a single obvious parameter, an agent can reasonably proceed.

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 description coverage is 0% — the schema offers only 'slug: string' with no description — so the description must compensate. It does not: 'slug' is never explained or even mentioned. The agent must infer that slug identifies the site from the tool name alone. With low coverage and no compensation, this is a clear gap.

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?

The description states a specific verb ('Publish'), a precise source resource ('the site's draft') and a target ('the LIVE site'), which clearly differentiates it from sibling tools like create_site, edit_site, and write_site_files. The 'hosted sites' qualifier adds useful scope.

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?

The description implies when to use it — to move a draft into production — and the parenthetical '(hosted sites)' hints at a scope restriction. However, it never explicitly names alternatives, states when NOT to use it, or clarifies prerequisites (e.g., a draft must exist). Usage context is inferred rather than stated.

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