run_pipeline

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

Without annotations, the description takes on the burden of explaining behavior. It discloses that the run executes asynchronously, returns a run_id, and requires polling for status and results. This is substantial behavioral context, though it could mention failure handling or validity checks.

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 sentences, front-loaded with the primary purpose and follow-up steps. Every clause serves a purpose with no redundancy or 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 complex asynchronous tool with no output schema and no annotations, the description covers initiation, return value, asynchronous behavior, polling, and final result retrieval. It references describe_pipeline for additional detail, making it complete enough for an agent to orchestrate the full pipeline lifecycle.

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%, and the schema descriptions already indicate that inputs and params are maps 'per describe_pipeline.' The description adds no meaning beyond the schema, merely restating the same guidance. This meets the baseline but does not elevate it.

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 clearly states the verb and resource: 'Start a pipeline run and return a run_id to track it.' This distinguishes it from sibling tools like list_pipelines, describe_pipeline, and get_run_status, which are explicitly mentioned as complementary follow-ups.

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 provides clear usage context by instructing to use describe_pipeline for input/param semantics and directing the sequence: poll get_run_status, then fetch get_results and get_provenance. It does not explicitly mention when not to use this tool, but the workflow is well-defined.

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