execute_custom_workflow

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

With no annotations, the description fully discloses behavior: immediate return with a status object, long-polling behavior of get_workflow_result, duplication risks on retry, and the meaning of pendingReason values including 'outsideWorkingHours' with its non-polling behavior. This goes well beyond minimal requirements.

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 organized into three focused paragraphs, each addressing a distinct aspect: retry warning, workflow lifecycle with follow-up tool, and pendingReason handling. Every sentence provides essential information without fluff, and the most critical warning is front-loaded.

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 description thoroughly covers the asynchronous execution flow, retry hazards, and pending scenarios, which is impressive for a complex tool. However, the lack of any detail about the 'definition' object structure is a notable gap, preventing a perfect score.

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 only parameter 'definition' is an object with 0% schema coverage, and the description merely restates that it is a workflow definition without detailing its structure or expected fields. The description adds no meaningful parameter guidance, leaving the agent without necessary construction details.

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 states a specific verb ('Execute') and resource ('a custom workflow definition'), clearly identifying the tool's action. It also distinguishes itself from sibling tool get_workflow_result by explaining the asynchronous handoff, making the purpose unambiguous.

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?

Explicitly instructs when not to retry (while still running) and directs to call get_workflow_result with the returned workflowId and operationName. It also explains how to interpret pendingReason values and when to report to the user rather than loop, providing clear usage guidance and alternatives.

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