Inspect managed application health

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

Adds substantial context beyond the annotations: the call actually queues an inspection via POST, requires a write-capable API key (read-only keys are rejected), needs applications:read, and can remain pending so results must be polled. These are exactly the non-obvious traits annotations (readOnlyHint=false, idempotentHint=true) cannot express.

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?

Five sentences with essentially no filler and the core purpose front-loaded. The permission/API-key sentence and the polling sentence are both load-bearing, though the block is dense enough that a shorter framing could convey the same payload.

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?

No output schema exists, yet the description covers the async/polling outcome, the follow-up tool and field to pass, and the auth requirement. Combined with annotations for the safety profile, an agent has everything needed to invoke and interpret this correctly.

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 coverage is 100% and both parameters (orderNo, installation_id) are fully described in the schema with patterns and formats, so the description adds nothing about them. It references inspection.id, but that is a response field, not an input. Baseline 3 applies when the schema carries the parameter burden.

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+resource+scope: 'Run an on-demand health inspection of one owned managed application and return the observed container/service health.' It also explicitly contrasts with the stale last-reported health, which is what sibling get_application_inspection surfaces, so an agent can distinguish the two without opening either 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 an explicit when-to-use ('Use this instead of trusting the last-reported health, which can be stale') and a concrete follow-up path with the alternative named: 'retain inspection.id and call get_application_inspection with kind=health'. Both the condition and the sibling are spelled out.

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