Publish or take offline a landing page

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

Far beyond the annotations, it discloses the full check suite (bracket text, password-request wording, Google Web Risk link checks, plan limits, 20 publishes/hour, workspace-accepted page rules), that nothing is published when a check fails and the answer lists per-block fixes, and scheduled items show at their set time. It also states the permission requirement (a key that may publish) and the idempotent retry guarantee, which is the key nuance the annotations cannot convey.

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 core publish/unpublish effects before the check and retry detail. The check enumeration is packed into one long sentence, but every clause carries information an agent would otherwise have to discover by failure.

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, open-world mutation with no output schema, the description covers what can go wrong (check failures, no partial publish), prerequisites (accepted page rules, publishing key), rate limiting, scheduling interaction, and safe retry. Nothing material is left for the agent to guess.

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?

At 67% schema coverage, the description adds real meaning: the publish/unpublish effect of each action value, and the retry-only semantics of idempotency_key (same key after a timeout returns the first answer rather than acting twice). pageId semantics are left implicit, which is minor since the pattern and required flag are in 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?

Both actions are stated with a concrete verb and effect: publish puts the page on the public web at its address or makes the latest draft live, unpublish takes it offline and keeps it as a draft. That distinguishes it cleanly from siblings like postfjord_create_page and postfjord_update_page, which manage content rather than visibility.

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 gives clear operating context: confirm with the owner first, unpublish when the page should go dark but be preserved, and a retry path with the same idempotency_key. It never names a sibling as an alternative (e.g. update_page for edits), so guidance is clear but not a full when/when-not routing.

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