Train Sft

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

With no annotations, the description must carry behavioral burden. It usefully discloses that the operation spends credits, a key side effect, but omits other important traits such as long-running execution, background processing, output format, idempotency, and checkpointing implications.

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 short sentences with zero waste. Purpose is front-loaded, followed by the critical cost warning. Nothing extraneous.

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 complex tool with a deeply nested schema, no annotations, and multiple sibling training methods, the description is far too sparse. It gives purpose and cost but no guidance on required inputs, background behavior, or how the operation relates to alternatives.

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% across a large nested request object, and the description adds no parameter meaning. It does not explain the required model/dataset structure, background flag, or any nested training/evaluation/checkpointing fields.

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?

States a specific verb and resource: 'Run Cookbook supervised fine-tuning.' The 'SFT' method distinguishes it from sibling training tools like train_dpo, train_rl, and train_distill, though no sibling is named explicitly.

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?

Provides a cost warning ('spends credits') but gives no guidance on when to choose SFT over DPO, RL, or distillation, nor any prerequisite or context for use.

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