dashai_predict

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

The description goes well beyond annotations by explaining that the tool creates a Prediction row and then enqueues a PredictJob, that the job expects prediction_id rather than run_id, that passing only run_id causes a KeyError, and that the operation is asynchronous. This is valuable behavioral disclosure beyond the readOnlyHint/idempotentHint flags.

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 well-structured: a one-sentence purpose, a clear async follow-up note, a concise two-step internal flow, a warning about a specific failure mode, and an Args/Returns recap. Every section adds important operational knowledge without padding.

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 the complexity of the two-step internal flow, the description covers the operation end-to-end: input semantics, async behavior, response shape, and follow-up tool. The KeyError warning is especially valuable for correct use of the returned prediction_id.

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?

The description includes an Args section explaining run_id as a finished run and dataset_id as optional with a default to the run's training dataset. It adds important context about the internal run_id/prediction_id distinction, though the input schema already provides detailed descriptions for the nested 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?

The description opens with a specific verb and resource: 'Enqueues a prediction using the model of an already finished run.' It clearly distinguishes this from training, dataset listing, and job-status tools, and it states that the operation is asynchronous and returns a job_id.

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 gives clear usage context: use it for a finished run, the operation is asynchronous like training, and the result should be followed via dashai_job_status. It does not explicitly enumerate when not to use it, but it provides enough contextual guidance for selection.

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