subnet_delete

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: it flags an audit tier ('review'), names the approval env vars (NUTANIX_AUDIT_APPROVED_BY/RATIONALE), explains irreversibility, and details what the audit trail captures (name, description, type, VLAN id, cluster, IP config and pools). This is rich behavioral context an agent needs before a high-risk mutation.

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 [WRITE][risk=high] and the core action, then the preview hint, then audit metadata, then Args. The risk/audit section is slightly verbose but every sentence conveys operational meaning. Overall tight and well-ordered.

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 high-risk destructive tool with no output schema and three zero-coverage params, the description covers the action, preview capability, audit/approval requirements, irreversibility, and all three parameters. It stops short of describing the return shape of dry_run output, but that is a minor gap for a delete 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?

Schema description coverage is 0%, so the description must carry parameter meaning. It does: ext_id is explained as 'Subnet extId as returned by subnet_list', dry_run is described as a no-op preview, and target is identified as the Prism Central target name from config with a default-omit rule. This fully compensates for empty schema descriptions.

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 ('Delete a subnet') and immediately adds the destructive nature and preview mechanism. Distinguishes itself from siblings like subnet_list/subnet_get/subnet_create by being the delete operation.

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?

Explicitly says to pass dry_run=True to preview before deleting, which is actionable when-to-use guidance. It does not name alternative tools or state when-not to use, but the preview-before-delete instruction is a clear usage directive.

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