Get application inspection

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

Annotations already cover safety (readOnly, idempotent, non-destructive, not open-world), but the description adds genuinely new behaviour: this call is non-queuing, it must be repeated with unchanged identifiers until succeeded/failed/expired, and it requires the applications:read scope. Only the polling/retry cadence and error behaviour (e.g. what a 404 on an unknown inspection_id means) are left unstated.

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 tightly packed sentences with the action front-loaded, zero filler, and the non-queuing constraint and terminal-state contract stated as short imperatives.

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 4-required-param polling tool with an inlined schema and no output schema, the description supplies the essential contract: the source of the inspection, the reuse-identifier rule, the terminal states, and the auth scope. It stops short of describing the returned payload shape or retry timing, which are the only remaining gaps.

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 only 50% — inspection_id and kind carry no schema descriptions — and the description compensates only partially by tying 'service, installation, inspection UUID and kind' together and implying the same values must be reused. It never explains what an inspection_id is or how orderNo relates to the tenant scope beyond what the schema already says.

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 precise verb ('Poll') and resource ('the exact persisted health or logs inspection') and explicitly scopes it as the follow-up to get_application_health / get_application_logs. An agent can immediately distinguish this tool from the two siblings that originate inspections.

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 the trigger condition ('when it remains pending'), names the alternative tools that would instead queue a new inspection, and states the exclusion 'This GET does not queue another inspection.' It also prescribes holding the same identifiers until a terminal state, covering when-to-use and when-not in one paragraph.

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