training_start

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

The description adds transparency beyond annotations by noting 'state-changing, may cost credits' and 'requires confirm_cost=true'. Annotations do not contradict this; readOnlyHint=false aligns with state-changing behavior.

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 concise, with two sentences that are front-loaded with the core purpose and key requirement. No unnecessary words.

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 10 parameters, a nested object (train_args), and no output schema, the description is too minimal. It lacks details on return values, error handling, or how to configure training via train_args, making it incomplete for a complex tool.

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?

With 50% schema description coverage, the description compensates slightly by clarifying that 'model' can be an existing ref or base checkpoint, and that confirm_cost must be true. However, many parameters (batch, epochs, imgsz, name, train_args) remain undocumented, leaving gaps.

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's action: 'Start a cloud training job' with specific sources (existing model or YOLO base checkpoint). It distinguishes from sibling tools like training_monitor and model_predict.

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 mentions a precondition ('Requires confirm_cost=true') but does not provide explicit guidance on when to use versus alternatives or when not to use it. The context is implied but not comprehensive.

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