create_databricks_job

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

With no annotations, the description carries the burden of behavioral disclosure. It explains that the tool runs asynchronously, requires polling, and performs a catalog scan. It does not mention potential limitations or error states, but the async behavior and outcome are well-communicated.

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 three sentences long, each serving a distinct purpose: stating the action, detailing the scan, and explaining the async workflow. No redundant information, and the most important elements are 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?

Given the tool has a single parameter and an output schema, the description covers the essential aspects: purpose, async behavior, and follow-up tools. It does not discuss error handling or edge cases, but for a straightforward creation tool, it is sufficiently complete.

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 only parameter, database_id, has 100% schema description coverage. The tool description does not add additional details beyond what the schema provides, but it correctly integrates the parameter into the overall task. A score of 3 is appropriate given high schema coverage.

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 states that the tool runs a GDLP classification scan on a Databricks database, specifying the verb 'Run', the resource 'Databricks database', and the action 'scan to identify sensitive data columns'. It distinguishes itself from siblings like 'create_job' and 'create_databricks_database' by being specific to classification scans.

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?

The description indicates when to use the tool (to run a classification scan) and provides clear follow-up steps: use 'get_jobs' to poll and 'get_classification_report' to view results. It does not explicitly state when not to use it or list alternatives, but the context is clear enough for an agent to decide.

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