run_workflow

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

With no annotations, the description carries the full burden and does disclose the most important non-obvious trait: caching keyed on (operation, version, params, inputs) with `force` bypassing it, plus the shape of the result. It omits execution characteristics such as duration, failure/partial-failure behaviour, and the cost of a large pipeline run.

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 action, then the caching caveat and the return shape. No filler or restatement of the name.

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 2-parameter tool with an output schema, the description covers the one genuinely tricky behaviour (cache reuse and `force`) and the return contract. The gap is the ambiguous `workflow` argument type, which neither schema nor description resolves.

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. It explains `force` well (bypasses cache), but says nothing about `workflow` being either an inline object or a string — an agent cannot tell whether the string is a path, a name, or serialised JSON.

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 ('Run a workflow or pipeline locally') and adds that it returns run_id, per-step outputs and workflow outputs, which separates it from validate_workflow/visualize_workflow/export_workflow. It does not explicitly name any sibling as the alternative, so the differentiation is inferential rather than stated.

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 a concrete usage scenario — cached step reuse means 'adding sessions to a dataset only runs the new ones' — and explains when to set `force`. It does not tell the agent when NOT to use it (e.g. validate first, or use get_run to re-fetch an existing run), so the guidance is contextual but not exhaustive.

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