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

Annotations only mark this as non-read-only, non-idempotent and non-destructive; the description adds substantial behavior beyond that — non-blocking return of an experimentId, a background thread, concurrency clamped via min(max_concurrent, 2), up to 3 queue-full retries per run, and polling each execution to completion. This is exactly the async/retry context an agent needs.

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 non-blocking, batch-scoped nature is front-loaded in the first clause, and every subsequent sentence carries operational detail with no filler. The middle sentence is dense and slightly run-on, but nothing is wasted.

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?

An output schema exists, so return values need not be described, and the description still explains the async model and points to experiment.get() for per-run status and aggregated metrics. Nothing needed to invoke or follow up on the tool 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 coverage is 100%, so both parameters are already documented, but the description reinforces the meaningful semantics: the 1-25 bound on the runs array and the min(max_concurrent, 2) clamping rule. It adds marginal clarification over the schema rather than new syntax.

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?

States a specific verb (Run) and resource (1-25 pipelines as one paced experiment), plus the async contract. It distinguishes itself from execution.run by scoping to batch runs that are submitted as a single experiment, which an agent can tell apart without opening either 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?

The description implies the use case (multi-pipeline batch, paced) and directs the agent to poll experiment.get() afterward, but never states when to prefer this over execution.run for a single run, nor any exclusion conditions. Usage is implied rather than spelled out.

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