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

Adds substantial context beyond the annotations: validates every step before any run, stops on first error, requires read/write/process permissions, completed steps are not rolled back or replayed, and commands are bounded by their normal timeout. These are exactly the behavioral traits an agent needs before triggering a destructive, open-world run.

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, then layers constraints in information-dense sentences; nearly every sentence earns its place. It is long, but the complexity of the tool justifies most of it.

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?

No output schema exists, yet the description names the return value (runId) and the lifecycle around it (poll or cancel). Combined with permission and timeout disclosure, an agent has everything needed to invoke and reason about the call.

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?

At 40% schema coverage the description usefully compensates for three of the parameters: inputs, the selected workSessionId, and expectedVersion's provenance and purpose. deviceId is left to the schema, and the description doesn't explain input key/value semantics, so it's strong but not complete.

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 precise verb (start one run) and resource (a saved workflow) with the input model made explicit. It clearly distinguishes itself from siblings get_workflow (review), workflow_status (poll), and cancel_workflow (stop), so an agent can route without ambiguity.

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 clear conditions: pass expectedVersion from get_workflow to refuse a stale definition, then poll workflow_status or cancel_workflow. It routes to the right follow-up siblings, though it does not explicitly state when NOT to use this tool versus a direct step call.

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