Run Experiment

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

With no annotations, the description carries the full behavioral burden and does so well: non-blocking return of an experimentId, a background thread capped at min(max_concurrent, 2), retry of queue-full up to 3 times per run, and polling to completion. It omits auth requirements and what happens on partial failure, but the concurrency/retry semantics are unusually well disclosed.

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?

Front-loads the critical behavioral fact '(NON-BLOCKING)' and the 1-25 bound, and every clause carries operational information. It is dense to the point of being slightly run-on, but no sentence is filler.

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 batch-execution tool with an output schema, the description correctly covers non-blocking semantics, scheduling behavior, and the handoff to get_experiment, so return-value detail is not needed. The only real gap is the shape of the `runs` array elements, which is not covered anywhere.

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%, and one parameter (`runs`) is an untyped array of open objects whose per-run shape is never explained. The description partially compensates by bounding `runs` at 1-25 pipelines and by clarifying that `max_concurrent` is effectively clamped to 2, but the structure of each run entry remains undocumented in both schema and description.

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 states a specific verb (run) and resource (1-25 pipelines as one paced experiment), and explicitly contrasts with the sibling polling tool get_experiment(). An agent can immediately tell this apart from run_pipeline (single run) and get_experiment (status polling) without opening any schema.

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?

It names the follow-up tool and the condition that selects it ('Poll get_experiment() for per-run status and, once finished, aggregated metrics'), and '(NON-BLOCKING)' tells the agent it can continue working after the call. It stops short of saying when to prefer run_pipeline over this batch tool, so it is clear context rather than full when/when-not guidance.

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