Guest Firewall Rules

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

Annotations already declare destructiveHint=true, and the description adds that create/update/delete operations are 'elevated' while list/get are queries. This usefully distinguishes safe read actions from privileged write actions. It does not detail specific privilege requirements or side effects, but the annotation coverage lowers the burden.

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?

Two compact sentences front-load the purpose and pack the action semantics efficiently using pipe-grouped clauses. Every phrase earns its place, with no filler or repetition of schema details.

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 action dispatcher and key enums are covered well, which is essential for this composite tool. However, with 20 parameters and no output schema, the description leaves meaningful gaps: it does not explain how update/delete identify a target rule (e.g., via pos or delete) or what list/get return. An agent may still need to guess when invoking certain actions.

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 only 30%, so the description must compensate. It does add valuable disambiguation for action, type, rule_action, and rule_type, especially separating the CRUD action from the firewall action. However, many parameters such as source, dest, proto, dport, sport, delete, pos, moveto, and enable remain unexplained, so the compensation is only partial.

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 ('Manage') and precise resource ('per-guest firewall rules'), which clearly distinguishes it from sibling cluster-level firewall tools. The action breakdown (query vs. manage) further clarifies what the tool does. No tautology or vagueness.

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 clear context: this is for per-guest rules, and action values are split into query (list/get) vs. management (create/update/delete). It does not explicitly name alternatives like proxmox_cluster_firewall_rule or state when not to use the tool, so the routing decision is partly left to inference.

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