Create generation run (async)

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

The description discloses async behavior (returns 202 with runId) and hints at polling, but does not cover error handling, rate limits, or consequences of invalid parameters. Since no annotations are present, the description carries the burden and partially meets it.

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 well-structured with a clear purpose line followed by delineated kind-specific parameter lists. While slightly verbose, it is organized and front-loaded, making it easy to parse.

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's complexity (three modes), minimal schema, and no annotations or output schema, the description covers the essential aspects: async launch, return value, polling hint, and detailed parameter definitions. It lacks only explicit prerequisites and error scenarios.

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 provides minimal structure (kind, orgId, generic params). The description compensates fully by detailing the param structure for each kind, including required and optional fields, enums, and constraints (e.g., doc_number ≤300, row_count ≤2000).

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 tool launches a generation run, distinguishes it from polling tools (get_run, wait_for_run), and details three different kinds with specific parameter sets.

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 guidance on post-launch actions (poll get_run or wait_for_run), implying when to use this tool vs siblings. However, it lacks explicit when-not-to-use or prerequisite conditions.

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