pipeline_run

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

Annotations indicate the operation is neither read-only nor destructive (readOnlyHint=false, destructiveHint=false), and the description adds 'on demand' but little else. It does not disclose that pipeline runs are often asynchronous, that a run may be long-lived, that it may consume resources, or that the caller should subsequently use pipeline_get_run_status. For a tool that triggers execution, the behavioral description is thin.

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 description is extremely short and front-loaded, with no filler words. 'Run a data pipeline on demand' conveys the action and resource in one clause. It could arguably be considered under-specified, but unlike a pure tautology, every word contributes meaning, so it earns a solid conciseness score rather than a penalty for verbosity.

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 run tool with no output schema, the description should explain what the caller gets back (e.g., an operation ID or run status) and how to track progress. It does neither. The sibling list heavily signals that pipeline_get_run_status and pipeline_cancel_run exist, but the description never routes the agent to them. Given that this is an initiating action with side effects and follow-up operations, the description is incomplete.

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 workspaceId, pipelineId, and parameters. The description adds no parameter-specific meaning beyond the schema, which is acceptable under the baseline rule: when the schema covers parameters, the description does not need to repeat them. It does not clarify what keys the parameters object should contain, but the schema's generic key-value definition covers that.

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 uses a clear verb ('Run') and resource ('data pipeline'), and adds 'on demand' to signal manual triggering. It is not a tautology like 'Process', and the resource type distinguishes it from run tools for other resources (notebook_run, copy_job_run), though it does not explicitly differentiate from pipeline_get_run_status or pipeline_cancel_run.

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?

There is no guidance about when to use this tool versus alternatives. The sibling list includes pipeline_get_run_status, pipeline_cancel_run, and pipeline_list_runs, and the description does not mention that this only starts a run, that there is a separate status-checking tool, or any prerequisites. Usage context is entirely implied by the name and one-line description.

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