create_firewall_policy

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

With no annotations, the description carries the full burden and delivers exceptional behavioral detail: local validation with ValueError naming, live controller verification, absence of the index field, the source-port filter footgun, and a runtime warning condition. These are exactly the non-obvious behaviors an agent needs before invoking an API.

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?

Although lengthy, the description is tightly organized: a one-line purpose, parameter definitions, and a clearly labeled PORT-FILTER PLACEMENT FOOTGUN warning. Every sentence contributes necessary information for correctly constructing a firewall policy with a nested schema.

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 complex create operation with an opaque schema and no annotations, the description covers host/site resolution, required fields, optional trafficFilter types, ordering via a sibling tool, zone ID sourcing, and a dangerous port-filter placement caveat. The presence of an output schema covers return-value expectations, so nothing critical is missing.

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?

The input schema is generic — policy is simply an 'additionalProperties: true' object — so the description supplies the entire semantic layer. It documents host formats, site addressing, required policy fields with types, the action/source/destination structure, and the trafficFilter one-of variants, fully compensating for 0% schema coverage.

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 opens with a specific verb and resource: 'Create a new firewall policy on a site.' It also differentiates from related siblings by explicitly stating there is NO 'index' field and directing rule-order management to set_firewall_policy_ordering, removing any ambiguity about scope.

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?

The description gives clear pointers to sibling tools for related tasks: use set_firewall_policy_ordering for rule order, list_firewall_zones_proxy for zone IDs, and list_firewall_policies for discovering in-use filter types. It does not explicitly state exclusions against update_firewall_policy or patch_firewall_policy, though 'Create a new' implies the distinction.

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