start_workflow

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

With no annotations, the description carries the full burden. It does disclose the creating side effect and the follow-up protocol (register workers, store results), which is meaningful. However, it omits other behavioral traits an agent might need: what the call returns (a workflow id to pass to register_worker?), whether creation is idempotent, what happens on name collision, and whether it runs asynchronously.

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?

Four sentences, each with a distinct job: state the action, give the trigger conditions, give the follow-up steps, and name the alternative. No filler or repetition; the most decision-relevant information (what this tool is for) is front-loaded.

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 description covers the core protocol and routes to siblings, but given 6 parameters, no output schema, and a required `name`, important context is missing: what the workflow run returns, whether the return value must be threaded into register_worker, and what `metadata`/`description` are used for. An agent can start using it, but may guess at linkage details.

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 only 33% (task_ids and binding_token documented; name, phases, metadata, description undocumented). The description adds at most an example for `phases` ('find→verify→synthesize') and the notion of schema-bound aggregation, but does not explain `metadata`, `name` conventions, or how the required `name` is used. Thus it fails to compensate for the sparse schema.

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 specific verb ('Create') and a precise resource ('first-class fan-out/fan-in WORKFLOW run'), and immediately clarifies the scope: multi-agent delegation, phased plans, and schema-bound aggregation. It also names the sibling tools it is not (plan_session/update_task), so an agent can disambiguate from the many workflow-adjacent tools in the sibling list.

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 lists the conditions that warrant this tool ('when a task will delegate to multiple agents, run phases such as find→verify→synthesize, or needs schema-bound aggregation') and gives a direct negative rule ('Do not use for ordinary single-thread task lists; use plan_session/update_task for those'). It also includes the required follow-up sequence with register_worker and record_structured_result, leaving no ambiguity about how to proceed.

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