cluster_info

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

With no annotations provided, the description carries the full behavioral disclosure burden. It only states that the tool retrieves information, implying read-only behavior, but gives no details about defaulting behavior, return payload, error cases, or whether state is read from the currently selected workspace.

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?

The description is a single focused sentence with no redundancy or fluff. It could be considered under-specified, but as a standalone sentence it is clear and front-loaded.

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 tool with no output schema, no annotations, and a workspace parameter that has no schema-level description, the single sentence leaves too much to inference: workspace selection semantics, return format, and relationship to set_workspace or compute context.

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 schema has 0% description coverage for the single workspace parameter, and the description does not add meaning beyond the parameter name. It fails to explain what accepted values look like, what null means, or how the workspace parameter relates to the active workspace context.

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 clearly identifies a read operation on a specific resource: Spark cluster information, scoped to a workspace. It is distinguishable from sibling list/set tools, though it does not specify exactly what cluster fields are returned or whether it targets the current compute context.

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?

No guidance is given on when to call cluster_info instead of other compute-related siblings such as set_workspace, set_warehouse, or list_lakehouses. It also does not state whether the optional workspace parameter overrides the current context or when omission is appropriate.

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