train_dataset_update

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

With no annotations provided, the description handles behavioral disclosure well. It discloses that captions are replaced, images are deleted along with caption files, refusal during active training, and returns per-file warnings for unknown files. Missing are details on atomicity or error handling, but core behaviors are covered.

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 with no waste. The first sentence front-loads the purpose and actions. Every clause earns its place, covering operations, constraints, and return behavior efficiently.

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?

No output schema exists, but the description mentions return of per-file warnings, partially addressing output. For a mutation tool with three parameters and nested objects, the description adequately covers inputs and key behaviors. Could mention success return, but not critical.

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 coverage is 100%, so the schema already documents parameter meanings. The description reinforces that captions can be set/replaced and images deleted, but adds little new semantic value beyond the schema's descriptions. Baseline score of 3 is appropriate.

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 specific verbs 'Edit' and describes actions 'set/replace per-image captions and/or delete images', clearly identifying the resource 'staged dataset'. It differentiates from sibling tools like 'train_dataset_delete' by focusing on content modification rather than full deletion.

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 explicitly states that the tool refuses while a training job is running/queued, providing a clear when-not-to-use constraint. However, it does not explicitly contrast with alternative tools for similar tasks (e.g., 'train_prepare_dataset'), though the constraint is valuable.

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