Delete firewall policy

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

Annotations already declare destructiveHint=true and idempotentHint=true, and 'IRREVERSIBLE' reinforces that rather than adding new facts. The genuinely valuable behavior — that the call only executes with confirm="YES" and otherwise returns a preview — appears only in the schema and is never surfaced in the description.

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 short sentences, front-loaded and waste-free. Brevity is appropriate for a delete tool, though the second sentence is emphasis rather than information.

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 destructive, gated mutation with no output schema and an undocumented required id, the description omits the most important operational fact: the confirm/preview safety gate. An agent could call this expecting deletion and instead receive a preview, or fail to pass confirm and be confused.

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 67%, and the required 'id' parameter has no schema description at all (what form is a firewall policy id?). The description says nothing about id, confirm, or dry_run, so it does not compensate for the coverage gap.

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 ('Deletes a firewall policy'), which cleanly separates it from the get/list/create/update/patch firewall-policy siblings. It stops short of explicitly naming those alternatives, but the operation is 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?

There is no guidance on when to use this versus list/get/update, no mention of required prerequisites such as the confirm token, and no note that a preview path exists. The agent gets a purpose but no decision criteria.

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