create_workflow

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

Without annotations, the description carries the full burden of behavioral disclosure. It explains the node structure, action types, and output propagation ({{nodes.<id>.body}}), giving insight into the definition schema. However, it does not disclose side effects (e.g., whether the workflow is created in draft mode), authorization requirements, or error behavior. This leaves gaps in understanding the tool's full behavior.

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 moderately long but well-structured: it begins with the purpose, then lists triggers, explains node structure with an example, lists action types, and mentions output propagation. Each sentence serves a purpose. It could be slightly more concise by omitting the output propagation detail, but overall it is efficient and front-loaded with the most important information.

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?

Given the tool's complexity (3 required parameters, nested objects, no output schema) and low schema coverage, the description is incomplete. It does not explain the return value, error conditions, or constraints (e.g., node count limits). It also omits details about the 'project_id' and 'name' parameters. The description is adequate for the 'definition' parameter but fails to provide a complete picture for successful tool usage.

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?

The schema has 3 parameters with only 33% description coverage (only 'definition' has a description). The description compensates for this by thoroughly explaining the 'definition' parameter, including its trigger, nodes, and action types with an example. However, it does not describe 'project_id' or 'name' beyond their names, leaving those parameters under-documented. The description adds value for one parameter but not for the others.

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 starts with 'Create a workflow,' which is a clear and specific verb+resource. It distinguishes from sibling tools like update_workflow and delete_workflow by focusing on creation details such as trigger types and node structure. The purpose is unmistakable and well-articulated.

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 provides no guidance on when to use this tool versus alternatives like update_workflow or execute_workflow. It does not mention prerequisites, conditions, or scenarios where creation is appropriate. The agent is left to infer usage context without any explicit instructions.

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