pve_sdn_apply

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

Without annotations, the description carries full burden. It discloses the mutation risk, dry-run behavior, possible async/sync return, and outcome field. It also warns about cluster-wide disruption. This covers key behavioral aspects sufficiently.

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?

The description is extremely concise with 4 short sentences, no filler. Key info is front-loaded (mutation, scope, dry-run). Every sentence adds value.

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?

Given the complexity (high-risk mutation) and presence of an output schema, the description covers return values (UPID/None, outcome) and dry-run. It lacks details on PLAN output interpretation and async behavior, but is largely complete for an informed agent.

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?

The description clarifies the 'confirm' parameter by explaining dry-run behavior, and hints at the 'proximo_target' parameter by mentioning 'which configured Proxmox target'. Schema coverage is 50%, so description compensates by adding context to both parameters.

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 clearly states the tool applies pending SDN config changes at cluster scope, with specific verb 'apply' and resource 'SDN config changes'. It distinguishes from other SDN tools (like pve_sdn_zone_create) and the sibling pve_network_apply by focusing on pending SDN changes.

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 explicitly says 'Dry-run by default' and 'confirm=True to execute', guiding when to use each mode. The high-risk warning implies caution, but it doesn't explicitly state alternative tools for modifying SDN config before applying. Still, it provides clear usage context.

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