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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond that by defining the result space (available / starting / offline) and the remediation path, which tells the agent what a non-ready result means.

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 short sentences, zero waste, with the core purpose front-loaded and the remediation tip second. Nothing redundant or padded.

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?

For a simple read-only status probe with no output schema, the description covers what the agent most needs: the possible states and how to move out of the 'offline' state. It does not describe the exact response shape, but with no output schema that omission is minor.

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 is effectively zero-argument, and the single schema property is self-documenting ('ignored — this tool takes no arguments'). With 100% schema coverage and no meaningful parameters, the baseline of 4 applies; the description correctly adds nothing further.

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 ('Check whether the Kaggle LLM brain is available') and enumerates the possible states (available, starting, offline). It is clear on its own, but never names or contrasts with the closely related siblings brain_complete, brain_run_task, or xmbl_status, so an agent must infer the boundary.

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 actionable context: if the brain is not available, 'Call POST /brain/start to activate it.' That is a concrete when/when-not signal. It falls short of 5 because it references an HTTP endpoint rather than sibling tooling and does not explicitly say when to prefer this over brain_run_task or xmbl_status.

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