Start DataLens Trino cluster

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so safety is partly covered. The description adds value annotations cannot: the billing consequence of a running cluster and the fact that it is experimental and untested. It still omits what happens if the cluster is already running (idempotency edge case).

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 tight sentences, front-loaded with the action and return value, then the cost warning, then the reliability caveat. No padding; every sentence changes agent behavior.

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 one-parameter start operation with no output schema, the description covers purpose, cost implications and experimental status adequately. The main omission is what to do if the cluster is not stopped and how to track the returned operation.

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?

Schema description coverage is 100% with a single documented cluster_id parameter, so the schema carries the load. The description adds no additional meaning about the parameter, which is the expected baseline here.

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 (Start) and resource (a stopped Trino cluster) and additionally names the return value (the operation that starts it). The 'stopped' qualifier implicitly but clearly distinguishes it from its sibling datalens_trinoclusters_stop without needing the schema.

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?

Explicitly scopes use to stopped clusters and adds a decisive routing condition: 'A running cluster is billed: ask the person before calling.' That is a real when-to-use gate, and the experimental/never-called note tells the agent to treat results cautiously.

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