Run Pipeline

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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) by disclosing that the run executes server-side as the owner with saved connections, returns {run_id, status: \"queued\"} immediately, enforces one-run-per-pipeline, produces a new pipeline version, and requires the create:models scope. These are exactly the operational traits 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?

A single dense block that is front-loaded with the action and return shape, with each subsequent clause adding a distinct operational fact (polling, duration cap, concurrency, versioning, scope). It is long for one paragraph but essentially waste-free rather than padded.

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 an async trigger tool with annotations and a sibling poller, everything needed to invoke correctly is present: inputs, immediate return, concurrency conflict handling, duration bound, and auth scope. An output schema exists, so return-value detail is covered structurally.

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 carry the load, and it does: pipeline_ref is explained as accepting a hash or id, and start_date/end_date are explained as YYYY-MM-DD values that limit source steps to that range. It stops just short of stating the date behavior when only one bound is supplied or the default full-refresh range.

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 refresh of one owned data pipeline') and immediately scopes it by identifier type (pipeline_hash or id). It is clearly distinguishable from siblings like get_pipeline_run and list_pipelines, which are referenced as polling/listing operations rather than triggers.

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?

Explicitly routes the agent: poll get_pipeline_run until succeeded/failed, with cadence guidance ('every few seconds'), expected duration, and the 30-minute stop. It also names the alternative behavior when a run is already active ('poll it instead of starting another').

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