Start training

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

Annotations already establish this is not read-only and not destructive. The description adds valuable non-obvious behavior: 'This may consume compute credits,' and indicates the job is tracked. It does not mention asynchronous completion or what artifacts are produced, but it covers the most decision-relevant side effect.

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 two short sentences with no filler. The primary purpose is front-loaded, and the compute-credit warning is placed second as a necessary caution. Every word earns its place.

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 tool with nine parameters, enums, defaults, and no output schema, this description is too sparse. It omits what the returned result is, how parameters interact, and what 'tracked' means operationally. The description covers intent and cost but not enough for confident invocation.

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%, so the description must compensate for the nine parameters, but it does not. None of name, epochs, preset, compute, project_slug, version_number, or existing_model_slug are explained. The phrase 'immutable dataset version' weakly alludes to dataset_slug/version_number, but it is insufficient to make parameter choices clear.

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 uses a specific verb-resource pair: 'Start a tracked training job,' which clearly identifies the action and distinguishes it from evaluation and workflow tools. It also adds the context 'against an immutable dataset version,' making the target of the operation concrete. This is a clear, non-tautological purpose statement.

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 conveys a clear context: it is for starting a training job rather than for listing, evaluating, or running a generic workflow. It does not explicitly name alternatives or provide exclusions, which prevents a 5, but the phrase 'tracked training job' gives enough contextual signal for an agent to know when this tool applies.

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