testWorkflow

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

The annotations declare destructiveHint=true and openWorldHint=true, and the description concretizes exactly what that means: real WhatsApp/SMS/email/call sends and CRM record mutation. It also adds consent requirements and the async contract (immediate execution_id, poll for result), which annotations cannot convey.

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?

Front-loads the core action and consequence in the first sentence, then the return/polling contract. Every sentence earns its place; only the trailing '(Tags: Workflows)' boilerplate is dead weight.

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?

Despite no output schema, the description fully explains the return shape (execution_id returned immediately) and the follow-up call needed to get results. Between the description, annotations, and schema, an agent has everything needed to call this correctly and safely.

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 3 is the baseline. The description adds meaning beyond the schema by clarifying that payload is the trigger data feeding node context and by constraining the values the user should put in it (their own phone number or email).

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?

States a specific verb and resource ('Runs the draft once with payload as the trigger data') and scopes it to a single execution of the draft workflow. It is clearly distinguishable from siblings like validateWorkflow, publishWorkflow, or activateWorkflow because it says the run is real, not a check or a state change.

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?

Gives a concrete precondition ('Ask the user before calling it') and a payload constraint ('use their own phone number or email'), plus routes polling to getWorkflowExecution. It lacks an explicit when-not or a named dry-run alternative (e.g. validateWorkflow), so it is clear but not fully exhaustive.

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