start_generation

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

Annotations already establish that this is not read-only, not destructive, and local. The description adds "local raw-text completion" and the greedy-decoding behavior, but it does not disclose whether the tool launches an asynchronous job, what lifecycle or resource implications apply, or what side effects occur beyond the annotations.

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?

Two sentences, front-loaded with purpose and then a key decoding rule. There is no filler, repetition, or unnecessary preamble.

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 job-launching generation tool with a complex request schema and no field descriptions, the definition omits most parameter semantics and says nothing about job lifecycle or asynchronous behavior. Output schema and annotations reduce the return-value and safety burden, but the description remains thin relative to the tool's complexity.

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 0% for the nested request object, and the description only explains one parameter: temperature=0 meaning greedy decoding. Valuable fields such as model, prompt, adapter, device, dtype, seed, and token limits are left to schema constraints rather than semantic explanation.

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 states a specific verb and resource: "Launch a local raw-text completion." "Raw-text completion" helps distinguish it from siblings like start_evaluation and start_fine_tune, though it does not explicitly name those alternatives or boundaries.

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?

It provides no explicit when-to-use guidance, no exclusions, and no alternative routing versus other start_* tools. The only usage-adjacent detail is that temperature=0 selects greedy decoding, so the agent must infer the intended use case.

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