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

Annotations already indicate this is not read-only and not idempotent, so a mutation is expected. The description adds value by stating the success return shape ({ workflowId, nodeCount }), the default source behavior when sourceConfig is omitted, and the unsupported graph category. It does not cover failure modes or rate limits, but for a create operation these are reasonable gaps given the annotations and the explicit return contract.

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 tight and information-dense: purpose, graph structure, prerequisite discovery call, success return, default source behavior, and an explicit unsupported case. Every sentence earns its place, and the core 'Create a new workflow' directive is front-loaded. There is no filler or repetition of schema details.

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?

This is a complex tool with nested graph and sourceConfig objects and no output schema. The description compensates well by describing the return contract, directing the agent to the authoritative node-type discovery tool, explaining the default sourceConfig, and capping applicability with the signal-intake exclusion. Combined with the 80% schema coverage, the agent has enough to invoke this correctly.

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 high at 80%, so the schema already documents name, graph, campaignId, workspaceId, and sourceConfig. The description adds meaningful parameter-level guidance beyond that: it explains that graph nodes are automation nodes with examples, that get_workflow_node_types should drive valid node configs, and that sourceConfig is optional with a concrete default. This pushes the value beyond the schema baseline.

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 the specific verb 'Create' and the target resource 'a new workflow', then clarifies what a workflow is: a graph of automation nodes and directed edges. It distinguishes itself from the many sibling tools by focusing on graph authoring and explicitly excluding signal-intake graphs. An agent can immediately tell this is the workflow-creation tool.

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?

The description gives explicit sequencing guidance: call campaignstack_get_workflow_node_types first to learn valid node types, configHint shapes, and the graph format. It also states a clear when-not case: signal-intake graphs with lead-list-based sources are not supported. The optional sourceConfig default behavior is spelled out, so the agent knows what happens if it omits the parameter.

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