Run Pipeline

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

With no annotations, the description carries the full burden and does well: it discloses the async/non-blocking contract, that an executionId is returned, and the exact polling lifecycle including terminal states. It omits permission/auth requirements and any note that this creates a persistent execution record, which a mutation tool should ideally state.

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 most decision-relevant fact (NON-BLOCKING) and the follow-up chain, then handles the one parameter worth explaining. No filler sentences.

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?

The async workflow and return contract are complete, and the output schema covers return values. However, the single required parameter train_graph is entirely undocumented, which is a meaningful gap for a tool whose core input is a graph object.

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 0%, so the description must compensate, but it only explains one of five parameters (layout's shape and the synthesized-grid default). The required train_graph payload, plus name, subject and description, receive no semantic guidance anywhere.

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+resource ('Start a pipeline run') and immediately signals the non-blocking execution model, which cleanly separates it from synchronous siblings like validate_pipeline and run_experiment.

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 an explicit follow-up workflow — poll get_execution() until completed/failed, then call get_results() — naming the sibling tools and the terminal states. It lacks an explicit when-not (e.g., 'validate_pipeline before running'), so it falls just short of a 5.

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