capabilities

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by stating it is 'structural — makes no network call and runs no preflight' and that output is returned in capability-enum declaration order for stability. That is genuine behavioral context not present in the annotations, though it doesn't cover latency or any failure modes.

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 key statement is front-loaded in the first sentence and the rest is dense, differentiated content rather than filler. It is somewhat long with several parenthetical asides ('a Redfish BMC has no video; a PiKVM has no BootProgress'), which slightly taxes scanning, but every clause carries useful routing information.

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 carries the return-value burden and does reasonably well: it explains the output is a capability list in enum declaration order and hints at items like video scope and live evidence. It stops short of describing the full returned structure or what a caller does with the result, so it is strong but not exhaustive for a no-output-schema tool.

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 the single `profile` parameter is fully documented in the schema, so the baseline of 3 applies. The description never mentions `profile` and instead discusses `video_scope`/`live_evidence`, which are not input parameters, so it adds no parameter-level meaning beyond the 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 ('List the capabilities the target's driver supports') and immediately scopes it as read-only and offline. It goes further than the sibling `info` by clarifying this is about *which interfaces a device can serve*, and differentiates concrete cases (Redfish BMC has no video; PiKVM has no BootProgress), so an agent can pick it apart from `info`, `healthcheck` and `support_matrix` without opening schemas.

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 usage context — 'so you can pick the right interface up front' — and names the alternatives with the conditions that select them: `support_matrix` for per-combo evidence, `healthcheck` for this exact device+firmware. It also draws a sharp boundary ('structural support is not live verification'), which is exactly the when-not-to-use guidance an agent needs.

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