Start DataLens Spark cluster

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

Annotations already cover the safety profile (non-read-only, non-destructive, non-idempotent, open-world), yet the description adds real behavioral context the annotations cannot: billing accrues while running, the call returns an operation rather than a completed cluster, how to resolve that operation (lakehouseoperations_get), and the "Experimental API, not measured" caveat.

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?

Front-loaded with the core action, then cost guidance and the operation follow-up; every sentence earns its place. The trailing fragment "Experimental API, not measured" is terse to the point of ambiguity, which slightly dents structure.

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 single-parameter mutation with no output schema, the description covers what an agent needs: the precondition, the cost consequence, the async return, and where to check the result. Annotations carry the safety hints, so nothing material is missing.

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?

Only one parameter (cluster_id) with 100% schema description coverage, so the schema already carries the meaning. The description adds no format or sourcing detail for cluster_id; the baseline of 3 applies for high-coverage schemas.

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 gives a specific verb and resource ("Start a stopped Spark cluster") with the precondition that the cluster must be stopped, which implicitly separates it from datalens_sparkclusters_create and datalens_sparkclusters_stop. It does not explicitly name a sibling to contrast with, so it stops just short of the top mark.

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?

"A cluster is paid for while it runs: start one only when asked to" is an explicit when-to-use (and when-to-refrain) rule grounded in cost. It does not point to alternatives such as creating a new cluster or starting a TriNo cluster instead, so it lacks the full alternative-routing of a 5.

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