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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is met structurally. The description adds a genuinely useful behavioral fact beyond them: the OpenRouter key itself is never returned, only its connection status — important for an agent reasoning about secrets. It stops short of noting auth/permission requirements.

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?

One compact sentence with no filler; every listed field earns its place. It reads as a fragment rather than a full clause, which slightly hurts front-loading clarity, but the density is appropriate for a trivial read tool.

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 compensates by listing the returned values, and annotations cover the safety profile. What remains missing is any statement of permissions or whether an unconnected key yields a partial result, but for a zero-arg settings read this is close to sufficient.

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 tool takes no parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It correctly avoids inventing parameter behavior for a zero-arg call.

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 enumerates exactly what is read back — key connection status, model, monthly spending cap, daily training proposal cap, current usage — which pins down the resource and scope (workspace AI configuration). It is a verbless fragment, so it never explicitly says 'retrieves', but the field list makes the purpose unambiguous and separates it from the mutating sibling update_ai_settings.

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 when-to-use guidance, no prerequisite, and no mention of the obvious alternative (update_ai_settings) or related reads like list_ai_models or get_training_overview. The agent must infer the call context entirely from the name.

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