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

Annotations only indicate readOnly=false, openWorldHint=true, non-idempotent, and non-destructive. The description adds meaningful behavioral detail beyond this: it spends LLM credits, returns immediately while running asynchronously, requires polling, suppresses duplicate re-runs, and requires OAuth 2.1. The duplicate-suppression note does not contradict the general idempotentHint=false caution because it describes a specific narrow same-input case rather than claiming full idempotency.

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 dense sentences front-load the core action and immediately warn about credit consumption. Every sentence contributes necessary operational information, and the polling instruction is especially valuable for an async tool.

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?

For a side-effecting, long-running tool with no output schema, the description covers the required inputs and their source, the return identifier, the polling lifecycle, duplicate suppression, and the auth requirement. Minor omissions such as specific error responses do not undermine an agent's ability to invoke and monitor the tool correctly.

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 schema already provides 100% coverage of both parameters, including that automation_id comes from list_automations and that transcription_id must be a completed transcription. The description largely restates these constraints rather than adding deeper parameter-level details, so the baseline score of 3 is appropriate.

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 names the exact operation ('Run one of the signed-in person's existing automations') and the specific resource it acts on ('one completed transcription'). It clearly distinguishes itself from related siblings like get_automation_run and list_automations by explaining that this tool initiates execution and returns a run_id immediately.

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?

It gives clear context for when to use the tool: run an existing automation over a completed transcription, requiring a user token and spending credits. It also explicitly instructs the agent to poll get_automation_run until succeeded or failed, which effectively defines the follow-up tool. It stops short of explicitly listing exclusions or when-not-to-use cases, so it is not a full 5.

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