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

Goes well beyond the read-only/open-world annotations: it discloses that anyone with the link can view the item, that early revocation is impossible, that access dies with edit permission, and that stale fetches may be cached. It also explicitly reconciles the 'creates' verb with the server's read-only marking, so no ambiguity is left for the agent.

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 purpose and state scope before the caveats; each sentence contributes a distinct operational fact (expiry, caching, refusal, return shape). It is dense — seven sentences — but not padded.

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?

No output schema exists, yet the description enumerates the returned fields and covers the permission prerequisite, the failure mode for published items, and the caching pitfall. An agent has everything needed to call this correctly and interpret the result.

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 post_id and expires_in_minutes are already fully documented with range and default. The description restates the same range/default and only adds the consequence that the link stops working at expiry, so baseline 3 is appropriate.

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States a specific verb and resource ('Creates a temporary preview link') and scopes it to unpublished items, enumerating the exact statuses (draft, pending, scheduled, private) and the effect (theme-rendered, no login). An agent can tell this apart from post-read or page-render siblings without opening the 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 clearly delineates the usable case (unpublished items) and the excluded case (a published item is refused with its public URL), which effectively tells the agent what to do instead. It does not name a sibling tool by name, so it falls short of the explicit 'use X instead' pattern.

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