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

Adds real behavioral context beyond annotations: the call is NON-BLOCKING and returns an executionId for polling. Annotations already cover the safety profile (not read-only, not idempotent, not destructive). It doesn't mention auth/permission requirements, which would be the remaining gap.

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 tight sentences, front-loaded with the core action and the non-blocking constraint, followed by the exact follow-up sequence. Every clause earns its place.

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 no elaboration, yet the description still surfaces the critical executionId and the async workflow. Combined with 100% schema coverage and annotations, nothing an agent needs to invoke this correctly 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 all five parameters including train_graph, layout, and subject. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 and resource ('Start a pipeline run') plus a key behavioral qualifier (NON-BLOCKING). It clearly distinguishes itself from execution.get/results by describing the start-vs-poll relationship, but does not differentiate from the sibling experiment.run, which also appears to initiate execution.

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?

Gives explicit next-step guidance: poll execution.get() until terminal status, then call execution.results(). This is strong forward-routing. It does not, however, state when to prefer this over experiment.run or any preconditions (e.g., a validated graph).

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