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

Annotations already declare destructiveHint and openWorldHint, but the description earns credit by specifying concrete external side effects (sending an email, writing to an ERP), stating that a draft test never activates the workflow, and describing the return payload (run status, run link, errors). It omits idempotency/retry behavior and whether a test run consumes quota or persists run history.

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?

Four short sentences, front-loaded with what the tool does, then consequences, then return value. No filler; only the missing sibling contrast keeps it from being exemplary.

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?

With no output schema, the description helpfully summarizes the return value, and it covers the safety warning well. Still missing are the idempotencyKey's role, input shape expectations for the nested object, and differentiation from dry_run/execute — gaps that matter for a destructive, open-world tool.

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 description coverage is 0% for 4 parameters, so the description must compensate. It adds meaning for inputs ('with the inputs you give') and implies versionId selects a saved version vs the open draft, but says nothing about workflowId format or the required idempotencyKey — a significant omission for a side-effecting tool with a nested object parameter.

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?

Names a specific verb and resource ('Starts one test run of a workflow') and clarifies it operates on either the open draft or a saved version. It does not, however, name or contrast with the obvious siblings workflow_dry_run and workflow_execute, which is the main ambiguity an agent faces here.

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 usage precondition — 'confirm with the user first' because steps act on connected systems — which is genuinely actionable. But it never states when to prefer this over workflow_dry_run (safe preview) or workflow_execute (real run), leaving the core routing decision to inference.

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