ai_capabilities

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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context: it reports 'actual' (runtime, not configured) state, and the caveat that 'Unavailable capabilities do not prevent connection' discloses partial-availability semantics an agent would not otherwise infer.

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?

Two sentences, zero filler, with the subject and scope front-loaded and the availability caveat placed second where it belongs. Every clause carries 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 and no parameters, the description still enumerates the returned fields (capabilities, targets, control owner, pause state), which is what an agent needs to know what it will get back. It does not describe the shape or format of those values, a minor remaining gap.

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?

The schema has zero parameters (additionalProperties: false), so per the rubric the baseline is 4. The description appropriately spends no words on parameter syntax it does not have.

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 names a specific verb ('Read') and enumerates the exact resource set: enabled capabilities, targets, control owner, and pause state, scoped to 'this approved connection'. That is far more specific than a tautology, though it never names or contrasts against a sibling such as ai_report, so the 5 tier for sibling differentiation is not met.

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?

There is no statement of when to call this versus alternatives, no prerequisites, and no when-not-to-use condition. The phrase 'for this approved connection' frames the subject but does not tell an agent when this tool is the right choice over ai_report or the apps_* family.

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