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

Annotations already cover readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the description does not need to repeat those. It adds useful behavioral context by stating that the created object is a draft and that the draft is the only mutable surface, which indirectly clarifies side effects. It could go further on failure/validation behavior when steps are invalid, but the schema and docs link mitigate that.

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?

Three dense sentences cover purpose, usage modes, documentation pointer, and lifecycle routing without redundancy. The core action is front-loaded, and every clause earns its place.

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, but the description plus the highly detailed input schema plus the presence of an output schema leave no significant gap. It provides the high-level model, the key parameter split, the documentation link for step-graph authoring, and the lifecycle sibling tools. An agent has enough to call it 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 coverage is 100%, so the baseline is 3, but the description adds value by explaining the semantic distinction between name (creates an empty draft) and steps (builds the graph up front). It also ties the steps parameter to a documentation URL for correct authoring. Environment and workspaceId are already well described in the 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 opens with 'Create a workflow' and defines it as a multi-step document pipeline, which clearly distinguishes it from sibling create_* tools that create classifiers, extractors, splitters, etc. It also sketches the pipeline stages (parse → extract/classify/split → validations → human review), giving an agent an accurate mental model of the resource.

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 explicitly maps different usage patterns: name alone creates an empty draft while steps builds the graph up front, and it directs the agent to get_documentation before hand-authoring. It also names the lifecycle alternatives — update_workflow for editing, deploy_workflow_version for freezing, run_workflow for running — so the agent knows exactly when create_workflow is the right call.

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