retrain_dataset

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

The description discloses the async nature (build runs asynchronously, returns immediately), the need to poll, and two specific error conditions (not_found and semantic_training_unavailable). These go well beyond the annotations, which only indicate readOnlyHint=false etc. The agent learns exactly what to expect and how to handle failures.

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 a tight 3-sentence block. The main action and async behavior are front-loaded, followed by usage guidance, parameter note, and error cases. Every sentence earns its place; there is no filler or repetition of schema text.

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?

Despite lacking an output schema, the description tells the agent what to expect (status and confirmation message) and how to obtain the final result (poll get_dataset_status). It covers the asynchronous workflow, parameter purpose, and failure modes. For a mutation tool of this complexity, nothing essential is missing.

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 100%, so the schema already documents both parameters. The description adds that epochs controls training length (and defaults/range, though those are also in schema) and clarifies that dataset_id comes from onboard_dataset or list_datasets, giving provenance. It does not deeply explain format or semantics beyond that, so a 4 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 opens with a clear verb-resource pairing — 'Re-trigger background semantic training for one dataset' — and specifies the immediate return behavior. It also names the related tool get_dataset_status, which distinguishes this tool as the trigger versus the status poller. The stated use cases (schema changes, alias updates, force rebuild) further pin down its purpose.

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?

Explicitly states when to use: 'after schema changes, alias updates, or to force a fresh model build'. It also tells the agent exactly what to do after calling (poll get_dataset_status until model_tier reaches 'schema'), effectively providing a follow-up action and an alternative tool. This leaves no ambiguity about the workflow.

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