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

Adds substantial context beyond the annotations: the ~24h order purge window, the requirement for a prior order_id, the fact that it returns a new order_id plus fresh DNS TXT records, and the correct follow-up sequence (poll propagation, then finalize). Annotations only supply the safety profile (write, non-idempotent, open-world), so this description carries the operational burden well.

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 sentences, front-loaded with purpose and mechanism, then the follow-up chain, then the fallback path. Every clause earns its place; the density is warranted for a tool embedded in a multi-step workflow.

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?

Despite an output schema existing (so return values needn't be explained), the description still states what comes back and what to do next, which is essential for orchestrating a multi-tool renewal sequence. Nothing needed to call it correctly or place it in the flow 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 coverage is 100% and the single parameter is fully documented there, so the baseline is 3. The description adds genuine value over the schema by tying the order_id to its short (~24h) lifetime and to the fallback tool, giving the agent a reason to check for the parameter's existence before calling.

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+resource ("Renew a certificate") and immediately pins down the mechanism (cloning a recent order). It also distinguishes itself from siblings create_certificate, check_certificate_propagation, and finalize_certificate by describing their respective roles in the flow.

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 explicit when-to-use (you have the original order_id), when-not ("If you don't have an order_id (the usual case at renewal time)"), and names the substitute tool create_certificate. It even resolves the conceptual trap that create_certificate *is* the renewal, leaving nothing to inference.

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