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

The annotations (all false hints) carry little information, so the description carries the burden — and it delivers: it discloses the success return shape ({ workflowId, nodeCount }), the default behavior when sourceConfig is omitted (campaign_pool with icpScoreMin 50), and the capability boundary around signal-intake graphs. It doesn't cover post-create execution side effects, but the key behavioral traits are surfaced.

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?

Six sentences, each earning its place: purpose, graph definition, prerequisite routing, return value, default behavior, and limitation. The core purpose is front-loaded in the first sentence, and there is no filler or repetition of schema content.

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 tool is complex (nested graph object, provider configs, no output schema), yet the description covers the prerequisite discovery step, return shape, defaults, and exclusions. The only meaningful gap is whether a created workflow begins executing immediately or requires a separate trigger — a behavioral detail an agent would want — but overall this is a well-rounded definition for a complex create operation.

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 80%, so the baseline is 3, but the description adds genuine value beyond it: concrete node type examples (linkedin:profile_view, linkedin:connection_request, flow:wait) that the schema doesn't enumerate, plus the practical consequence of omitting sourceConfig. These details help an agent construct a valid graph and decide whether to pass sourceConfig at all.

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 opens with a precise verb+resource ('Create a new workflow from a graph you author') and immediately defines what a graph is — automation nodes plus directed edges. This distinguishes the tool from its workflow siblings (get_workflow, update_workflow, delete_workflow, trigger_workflow, list_workflows) without needing to inspect any of them.

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?

It gives an explicit prerequisite, 'Use campaignstack_get_workflow_node_types first to discover valid node types, their configHint shapes, and the required graph format,' which routes the agent to the correct discovery tool. It also states a clear when-not boundary ('Signal-intake graphs... are not supported by this tool'), though it doesn't name the alternative tool for that unsupported case.

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