ban_ips

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context beyond that: validation is all-or-nothing ("All IPs are validated before any is banned") and the effect is synchronous ("Acts on the instances immediately"). It does not mention permission requirements or what the response contains, which is the remaining gap.

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?

One tight paragraph with the scope statement front-loaded and the sibling pointer at the end. A minor portion restates schema fields, but no sentence is wasted and nothing important is buried.

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 single-parameter, non-read-only tool with no output schema, the description covers scope, atomicity, immediacy, expiry semantics, and the undo path. Only the auth/permission preconditions and post-call result behavior are left unstated.

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 the schema already documents ip, exp (0 = permanent), reason and service. The description's restatement of the payload fields and the exp/service semantics adds little beyond that; the atomic-validation note is behavioral rather than parameter-level. Baseline 3 is appropriate.

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?

"Ban IPs on every instance" gives a specific verb, resource, and blast radius, and the list payload shape {ip, exp, reason, service} is spelled out. It is unambiguously distinct from the siblings unban_ips and list_bans.

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?

It names the counter-tool explicitly ("Use unban_ips to lift a ban") and explains the scope selector ("service omitted for global"), which is the main decision an agent must make before calling. Missing an explicit when-not-to-use clause, e.g. whether to prefer a per-service ban over a global one, keeps it out of 5 territory.

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