pve_sdn_rollback

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

With no annotations provided, the description fully discloses behavioral traits: mutation (destructive), risk medium, bounded to config plane, discards all pending edits, dry-run default, confirm=True execution, return format, no undo, and lock_token not written to audit ledger. This is comprehensive.

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 detailed but well-structured with front-loaded key information. It is not overly verbose, though some sentences could be tightened without losing meaning. Overall, it earns its length.

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?

The description covers purpose, behavior, parameters, side effects, risks, and return values (including output schema). It is fully complete given the tool's complexity and available context signals.

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 baseline is 3. The description adds behavioral context beyond schema (e.g., lock_token never written to audit ledger, release_lock default true, proximo_target for multi-target). This adds meaningful value, raising the score to 4.

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 it is a mutation that discards all pending SDN configuration changes cluster-wide, explicitly calling it the 'real undo primitive'. It distinguishes itself from pve_sdn_apply (live networking) and pve_sdn_dry_run, making the purpose unambiguous.

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 provides explicit guidance: when to use (want to discard pending SDN config), when not to (for live networking, which belongs to pve_sdn_apply), dry-run default with confirm=True to execute, and cautions about cross-node inconsistency from failed applies. It also notes no undo of its own.

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