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

Goes well beyond the annotations: enforcement latency (~10 seconds), a hard cap of 5 firewalls per machine, additive rule semantics, the public-address prerequisite, and the required scope network.write. The 'Attaching again is harmless' note reinforces idempotentHint with plain-language confirmation rather than contradicting it.

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?

Four short sentences, front-loaded with the behavioral consequence before the limits and failure condition. Minor friction from the elliptical phrasing 'no rule of its firewalls opens', which takes a moment to parse, but nothing is padding.

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 two-parameter mutation with no output schema, the description covers the resulting state, propagation delay, quota, prerequisites, idempotency, and permission scope. The only real gap is the absence of any routing to the detach/update siblings for the inverse or modification operations.

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 100% (vm and firewall are both documented with provenance from list_vms/create_vm and list_firewalls/create_firewall), so the schema carries parameter meaning. The description adds nothing about the two parameters, so the baseline 3 applies.

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 defines the tool by its effect ('the machine refuses inbound traffic no rule of its firewalls opens') and the idempotency note implies an attach action, which the title 'Attach a firewall to a machine' confirms. It is distinguishable from detach_firewall and set_rules by its additive, per-machine scope, but the core verb is never stated outright in the description text itself.

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?

Usage is implied by the effect statement and the prerequisite 'Refused for a machine with no public address', which tells the agent when a call will fail. However, no sibling is named and there is no explicit guidance contrasting this with detach_firewall, set_rules, or update_firewall.

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