Create workflow

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

Annotations provide openWorldHint=false and destructiveHint=false. The description adds behavioral details beyond these: it returns the new workflow with id and hook URL for webhook trigger, and clarifies defaults. It does not contradict annotations.

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?

Two concise, front-loaded sentences that convey all essential information with zero wasted words. Every clause adds value.

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 no output schema, the description adequately explains the return value (the new workflow id and hook URL for webhook). It covers the key parameter interactions and defaults. A minor gap: it doesn't mention that agent_id is optional and its purpose (recording creator), but the schema description covers that.

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 description adds value by explaining the effect of trigger_kind (default 'manual') and conditional requirements (cron_expr needed for 'cron'). This context is not present in the schema descriptions.

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 clearly states the tool creates an empty workflow and that steps are built separately. It distinguishes itself from siblings like 'run_workflow' (which runs workflows) and 'list_workflows' (which lists them), and from 'create_agent' which is a different 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?

The description explains when to use each trigger_kind: 'manual' is default, 'cron' requires a cron_expr, 'webhook' returns a hook URL. It implicitly tells the AI not to use this tool to build steps, but doesn't explicitly name alternative tools for building steps, which would be ideal.

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