unpublish

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

Goes well beyond the destructiveHint=true annotation by describing exactly what destruction means: delivery stops serving (URL 404s), referencing content areas drop it, a content.unpublished webhook fires, and version history is retained while other locales are untouched. This is exactly the added context the annotations do not carry. The remaining minor gap is no note on permissions or whether the webhook is synchronous, which keeps it short of a perfect 5.

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?

Six short sentences, each carrying a distinct fact (delivery effect, references, webhook, retention, locale scope, alternative), with the primary effect front-loaded. No filler or restatement of the tool name.

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 destructive, non-idempotent mutation with no output schema, the description supplies everything needed to call it safely: the exact observable consequences, reversibility via publish, locale scoping, and the escape hatch to trash_content. Nothing material 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?

Schema description coverage is already 100%, so the baseline is 3, but the description adds real meaning to 'locale' by framing the operation as per-locale and asserting other locales are unaffected, which clarifies the blast radius of that parameter. It does not add syntax or format detail for site/documentId beyond the schema, so it lands just above baseline.

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 (take off the live site) and resource (content item), scoped explicitly to one locale. It distinguishes itself from trash_content and publish by naming both endpoints of the lifecycle, so an agent can tell it apart from siblings 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?

Names the alternative (trash_content) with the condition that selects it ('To remove the item entirely'), and spells out the reversible nature ('publish brings it back') that makes this the non-destructive-takedown choice. The when/when-not pair is explicit rather than inferred.

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