getGatewayHealth

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real operational context beyond that — it discloses hidden discovery work ('auto-discovers the site gateway') and that supplying gatewayMac skips it. It does not say what happens when a site has no gateway or multiple gateways, nor how expensive the discovery listing is, but the composite nature and the discovery shortcut are meaningfully surfaced.

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?

Three sentences, front-loaded with the composite payload and its three components, then the diagnostic use cases, then the optimization hint. Every clause carries information an agent would act on; nothing is padding or restatement of the tool name.

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 no output schema, the description compensates by enumerating the returned fields (CPU, memory, firmware, ports, WAN link state/IP/ISP, LAN statuses), which is enough for an agent to know what it will get back. The only gap is failure behavior — no mention of the outcome when discovery finds no gateway or when siteId is invalid.

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 both siteId and gatewayMac are already documented, including the default-site fallback and the auto-discovery behavior. The description's 'Optionally accepts a gatewayMac to skip discovery' largely restates the schema; it adds the framing of discovery as a cost to avoid but no new syntax or constraint details. Baseline 3 for a fully covered schema.

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?

States a specific verb and resource ('Composite gateway health check') and immediately enumerates the three data classes bundled: gateway detail (CPU, memory, firmware, ports), WAN port statuses, and LAN interface statuses. The word 'composite' distinguishes it from the granular siblings getGatewayDetail, getGatewayWanStatus, and getGatewayLanStatus without the agent needing to open 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?

Gives explicit triggering conditions: 'diagnosing internet connectivity issues, WAN failover, or gateway performance problems.' That is solid when-to-use coverage. It stops short of naming the granular alternatives (getGatewayWanStatus, getGatewayLanStatus) as the choice for narrow single-aspect queries, leaving that inference to the agent.

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