iaas_create_compute_nat

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered externally, but the description adds nothing beyond that: no statement about whether the call provisions a request/task tracker, whether duplicate names are rejected, or what happens on failure. For a create/mutation tool it should carry more, or at least confirm the async/blocking nature that the sibling naming convention hints at.

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?

It is short, but three lines say the same thing, so nothing is front-loaded except a redundant restatement. The one genuinely useful token (the endpoint path) is buried at the end instead of the description spending its length on prerequisites or the required body fields.

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 create is a mutation with a rich nested body and no output schema, so the return value is undocumented internally and externally. Given the schema's completeness and the annotations covering safety, the description still leaves one important thing unstated — whether the create is synchronous or returns a request tracker to poll — but the structured data carries enough that an agent can construct a call.

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%, so the nested body schema already documents 'gateway', 'natRules' (with kind/type/index/targetLink and defaults) and 'projectId' thoroughly; the description adds nothing on top. Per the high-coverage baseline, 3 is the ceiling here.

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 restates the tool name three times ('Create a Compute Nat' / 'Create a new Compute Nat.' / 'POST /iaas/api/compute-nats') with no elaboration. The only information not already in the name is the HTTP endpoint. It also does not distinguish this create operation from the nearby iaas_reconfigure_nat, iaas_delete_compute_nat, or iaas_get_compute_nat siblings.

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 iaas_reconfigure_nat (modifying an existing NAT) or iaas_create_compute_gateway (a prerequisite for the required 'gateway' field), no mention of prerequisites, and no exclusions. The verb alone implies the use case, which is the minimum implicit signal, not real guidance.

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