rollback_website

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

Beyond the destructiveHint/readOnly annotations, the description adds critical behavioral safety: the agent must present the exact returned target version and commit, get explicit confirmation, and never infer or guess the template ID. It also discloses the return value (worker job ID) and the follow-up polling tool, get_deployment.

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, front-loaded with the core purpose and followed by essential safety and follow-up guidance. Every sentence adds distinct value; the IMPORTANT marker appropriately emphasizes the irreversible-confirmation step.

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 two required parameters, a full schema, and an output schema, the description still covers the prerequisite call, the confirmation protocol, the return value, and the polling follow-up. An agent has everything needed to invoke the tool correctly and safely.

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 the baseline is 3. The description adds meaningful guidance on templateId semantics: it must be the exact returned, commit-pinned version from list_rollback_versions and must never be inferred or unverified, which goes beyond the schema's one-line description.

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?

The description names a specific verb ('roll back') and resource ('static website') and qualifies the target as 'a specific commit-pinned template version.' This clearly distinguishes it from redeploy_website and other deployment mutations.

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 explicit prerequisites: call list_rollback_versions first, and only use a returned version after confirmed user approval. It stops short of naming alternative tools for non-rollback redeployment, but the context is clear enough for an agent to decide when to call it.

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