Create DataLens Spark cluster

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

Annotations already declare non-read-only, non-idempotent, open-world, non-destructive, but the description adds value they don't carry: the cluster is billed while running, creation is asynchronous (the operation outlives the reply), how to poll it, and that the API is 'experimental, not measured.' That is exactly the extra behavioral context annotations cannot express.

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 action, then cost warning, then post-call polling, then an experimental caveat — every sentence carries distinct information. The middle sentence about the operation continuing 'after the reply' is slightly convoluted but earns its place.

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 nested-config mutation with no output schema, the description covers cost, asynchrony, how to resolve the operation, and experimental status. The main remaining gap is a note on the required collection/cloud-environment scoping, which the schema handles adequately.

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%, so collection_id, cloud_environment_id, name and the deeply nested config are already fully documented. The description adds no parameter guidance (e.g., nesting of resourcePools or sparkVersion defaults), so the baseline 3 applies.

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 precise verb+resource ('Create a Spark cluster') and even discloses the return shape ('return the operation that creates it'). Among the many datalens_sparkclusters_* siblings (list/get/start/stop/delete), 'create' is unambiguous, and the mention of lakehouseoperations_get signals the async follow-up path.

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?

Explicit when-not guidance tied to cost: 'A cluster is paid for while it runs: create one only when asked to.' It also tells the agent what to do after the call ('lakehouseoperations_get with its id says how it ended'). It does not compare against start/stop or reuse of an existing cluster, so not a full 5.

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