Get network references

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

Annotations already establish readOnlyHint/destructiveHint=false, but the description adds substantial unstated behavior: the precise return structure and a documented controller bug (HTTP 500 api.unexpected-error on 11.0.83) with a working fallback procedure. That is exactly the kind of environment-specific behavior an agent cannot get from annotations.

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?

Purpose is front-loaded and every sentence carries weight (purpose, return shape, usage, failure fallback). It is slightly long, and since an output schema exists, enumerating the return shape in the description is mildly redundant, keeping it just under a 5.

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?

With an output schema and safety annotations already present, the description still covers everything else an agent needs: dependency-finding intent and a fully specified recovery path for the known 500 error. Nothing required to invoke it correctly 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?

Schema description coverage is 100% and both required params (siteId, networkId) are fully documented in the schema with patterns. The description adds no syntax or semantic detail for the parameters, so the baseline of 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?

The description states a specific verb (Get) and resource (objects that reference this network) and immediately clarifies the returned relationship shape. It is clearly distinguishable from siblings like unifi_get_network or unifi_list_networks, which return the network itself rather than its dependents.

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 gives an explicit trigger ("Use before deleting a network to find dependencies that need to be re-pointed or removed") and, on failure, names concrete alternatives (unifi_list_wifi + unifi_get_wifi, unifi_list_firewall_zones) with the exact field paths to inspect. This is model when-to-use/fallback guidance.

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