Refresh Automatic SSL status

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

Annotations cover idempotency, non-destructiveness and open-world reach, and the description adds genuinely new context: the operation is durably scheduled (async), it does not re-issue a provider mutation, and it requires the certificates:manage permission. The 'read-only' phrasing sits in mild tension with readOnlyHint=false, but the description reconciles it by clarifying only the CA refresh itself is read-only while the scheduling is a persisted write.

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?

Four short sentences, each earning its place: action and scope first, then the trigger condition, then post-call polling, then the permission prerequisite. No filler and the most important routing information is front-loaded.

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 output schema, the description compensates well by telling the agent to poll get_automatic_ssl_subscription and list_automatic_ssl_actions for the outcome, and it covers the auth prerequisite. It stops short of describing what the immediate call returns (e.g. a job/action handle), which is the only remaining gap for an async scheduling tool.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the UUID pattern and its source (list_automatic_ssl_subscriptions). The description adds the ownership constraint ('one owned ... subscription') but no format or lookup detail beyond that, so the baseline 3 applies.

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: 'schedule an authoritative read-only certificate-authority refresh for one owned Automatic SSL subscription.' The scope ('one owned Automatic SSL subscription') separates it from generic certificate siblings such as refresh_certificate or recheck_certificate_validation, and it names the read tools it is not (get_automatic_ssl_subscription, list_automatic_ssl_actions).

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?

Gives a clear trigger condition — 'Use it for stale or ambiguous state' — and directs the agent to the polling tools afterward. It also implies a when-not boundary ('it never repeats a provider mutation'), but does not explicitly route to cancel_automatic_ssl_subscription or other SSL siblings for non-refresh intents.

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