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

Annotations already mark this as non-read-only and non-idempotent, and the description adds useful context that running a flow is asynchronous, returning a workflowRunIdentifier that requires flows_wait and creations_show. However, it does not disclose potential side effects such as credit consumption, external generation, or failure behavior.

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?

Three tight sentences convey the core action, prerequisites, input mapping, and expected follow-up sequence. Every clause adds value and the front-loaded 'Run flow' makes the purpose immediately clear.

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 the lack of output schema and sparse annotations, the description outlines the full invocation chain: flows_get → run → flows_wait → creations_show. It covers the essential workflow lifecycle, though it omits auth requirements, error handling, and cost implications that could be relevant for a flow-execution 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 coverage is 0%, so the description carries the burden. It helpfully explains the shape of inputs as {inputId: value} and gives concrete source examples, but it does not explicitly explain the identifier parameter beyond the implicit context that flows_get should be called first. This is partial but not complete compensation.

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?

Starts with a clear, specific verb and resource: 'Run flow.' It distinguishes itself from sibling tools like flows_get, flows_list, and flows_wait by describing its role as initiating execution and returning a workflowRunIdentifier that feeds into flows_wait and then creations_show.

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 to call flows_get first for input specs, and clarifies where input values come from (creations_list, audio_voices_show). It provides clear context for when to invoke this tool in a workflow, though it does not state explicit exclusions or alternatives beyond the implied prerequisite chain.

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