create_ml_project

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

Annotations already indicate it's not read-only (readOnlyHint=false), so the description need not repeat that. It adds context about the verification step ('This tool verifies that first and returns an actionable error otherwise') and explains the URI construction from server_id/caslib_name/table_name. This goes beyond annotations and helps the agent understand side effects and dependencies.

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 tightly worded, with the core purpose stated first, followed by essential prerequisites and guidance. There is no fluff; every sentence contributes value. The structure is clear and front-loaded, making it easy to scan.

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 complexity (9 params) and the existence of an output schema, the description covers the critical aspects: prerequisites (table in global scope), verification behavior, and URI construction. It doesn't need to explain return values since an output schema exists. The description is complete for the agent to understand when to use it and what it does.

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 coverage is 100%, so all parameters have descriptions. The description adds extra meaning by explaining that the training table must be loaded globally and that the URI is built from server_id/caslib_name/table_name, which clarifies the relationship between those parameters. This added context goes beyond what the schema provides.

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 the action: 'Create a new AutoML pipeline automation project from a CAS table.' It specifies the resource (CAS table) and the purpose (AutoML pipeline automation), and it distinguishes itself from sibling tools like run_ml_project (running a project) and list_ml_projects (listing). This is a specific verb+resource pair with clear differentiation.

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 provides explicit prerequisites: 'The training table must already be loaded into CAS memory at **global** scope.' It even names alternative tools for preparation: 'use promote_table_to_memory to load + promote a source table, and list_source_tables to find one.' This gives clear when-to-use and when-not-to-use guidance, and points to alternatives for those prerequisites.

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