capabilities

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

The description adds substantial context beyond annotations: it states the tool makes no network call and runs no preflight, returns in enum declaration order for stable output, and clarifies that live_evidence is not live verification. This is rich behavioral disclosure, fully consistent with the readOnly and idempotent annotations.

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 a clear definition, then efficiently expands with structural details, examples, and tool comparisons. Every sentence earns its place, and the structure with line breaks aids readability without bloat.

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?

The description covers the tool's purpose, output ordering, the meaning of live_evidence, and alternative tools, which is comprehensive for a simple query tool. However, it omits any explanation of the 'profile' parameter, and with no output schema, this is a minor incompleteness.

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?

With 0% schema description coverage, the description needed to explain the 'profile' parameter, but it makes no mention of it. The parameter is optional with a default of null, yet the description provides no guidance on its meaning or effect, leaving a clear gap.

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 clearly states the tool 'List the capabilities the target's driver supports' with a specific verb and resource. It distinguishes itself from siblings by contrasting with support_matrix and healthcheck, making the tool's unique role obvious.

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 provides explicit usage context: 'so you can pick the right interface up front' and gives concrete examples (Redfish has no video, PiKVM has no BootProgress). It also names alternatives for different needs, telling users to call support_matrix for per-combo evidence and healthcheck for this exact device+firmware.

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