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

Adds material context beyond the annotations: the link is private, expires in 15 minutes, images are suppressed, and enquiries are disabled. The safety profile is already covered by the read-only/idempotent hints, so the remaining gap is minor; it does not say what happens if no draft has been saved.

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?

Three short sentences with zero waste. The most decision-relevant facts (what it returns, how long it lasts) are front-loaded, followed by usage and limitations.

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?

With no parameters and no output schema, the definition covers what the agent needs: that a link is returned, its lifetime, and what the recipient will and will not see. It could mention the prerequisite that a saved draft must exist, but otherwise it is self-contained.

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?

The tool takes no parameters, so the baseline is 4 and the description correctly adds nothing about inputs. There is no ambiguity for the agent to resolve.

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 and resource: return a private link to the saved draft. It also distinguishes itself from the publishing siblings by framing the link as something to review 'before publishing', so an agent can separate it from publish_site and get_site.

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 gives clear context for use: when the owner needs to review a draft prior to publishing. It does not explicitly name when not to use it or which sibling to use instead (e.g. get_site for published content), leaving the exclusion to inference.

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