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

Beyond the annotations (which already declare readOnlyHint, idempotentHint, non-destructive, non-open-world), the description discloses the auth model (Last Price credential) and a specific failure mode: self-registered sandbox keys get 403 until a human claims the workspace. It also previews what state information comes back, so the agent knows diagnostic value is included, not just a bare list.

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 short sentences, front-loaded with what is listed and what the caller learns, then safety, then preconditions. No filler, and the 'Read-only' note is the only slight redundancy against the annotations.

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 params and no output schema, the description carries the burden of explaining the response, and it does: available/loaded/why-not-loaded per backend. Combined with annotations covering safety and the description covering auth and error behavior, an agent has everything needed to call it and interpret a 403.

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 zero parameters, so there is nothing for the description to disambiguate; baseline for a no-param tool applies. The description correctly avoids inventing arguments and focuses on output meaning instead.

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 inference backends the AITune sidecar offers your workspace') and then enumerates the returned state dimensions (available, loaded, why not loaded). The AITune-sidecar framing distinguishes it from generic siblings like list_inference_providers or list_hosted_models without needing to name them.

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 concrete preconditions for use: a Last Price credential is required and the workspace must be claimed, with the sandbox-key case explicitly refused with 403. It stops short of naming alternative tools for adjacent needs (e.g., provider listing vs backend listing), so it is clear context but not a full when/when-not routing guide.

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