list_unifi_devices

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'Read-only operation,' so there is no contradiction. It adds genuine value beyond the annotation by disclosing the return contents (name, controller URL, site, services, network-only/protect-only lists) and the response shape (Dict with total_devices, per-device list, and name lists), which is especially useful given there is no output schema. It stops short of a 5 because it does not address edge cases such as behavior when no consoles are configured.

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?

The description is front-loaded with the core action, then a compact paragraph of functional detail, an alternative-routing sentence, and a clearly formatted Returns section. Every sentence earns its place — no filler, no repetition of schema or annotation content — and the ~120-word length is appropriate for a tool that must compensate for the absence of an output 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 zero-parameter, read-only list tool with no output schema, the description covers everything an agent needs: exact scope, return fields and structure, and sibling routing. The explicit 'Returns:' section is a significant completeness win given no output schema exists; the only omission is edge-case behavior (e.g., empty roster), which is minor for this operation.

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 tool takes zero parameters, so there is nothing for the description to explain beyond the schema; the 100% (vacuous) schema coverage and the 0-parameter baseline of 4 apply. The only parameter-related information, the 'device' parameter accepted by other tools, is correctly positioned as context for where this tool fits rather than as an input to this tool.

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+resource: 'List every UniFi device (console) configured for this server,' which precisely defines the tool's scope. The parenthetical '(console)' plus the explicit contrast with get_global_inventory / get_global_health ('aggregated data across those consoles rather than the console roster itself') distinguishes it from sibling tools without opening any schema.

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 explicitly names alternatives: 'Use get_global_inventory / get_global_health when you instead want aggregated data across those consoles rather than the console roster itself,' giving a clear when-not condition. It also positions the tool as 'the authoritative source for the device name accepted by every other tool's optional device parameter,' telling the agent exactly when to call it — when a valid console/device name is needed for downstream calls.

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