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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false, openWorld=true), it discloses credit consumption, that the cost was shown at prepare time, that the run takes minutes and requires polling, and that it needs a signed-in account. These are meaningful behavioral traits annotations cannot express.

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 the core action, then progressively disclosing cost, latency/polling, and auth. No filler and every sentence carries operational meaning.

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 an output schema present, return values need no explanation, and cost/latency/auth are all covered. The only gap is that the required project_id parameter is left entirely to the schema, which itself has no description.

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% and the single parameter (project_id) is never mentioned or explained in the description. The phrase 'the prepared run' hints at what is being started but gives no syntax, format, or constraint for the required project_id.

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 states a specific verb and resource ('Start the prepared run') and situates it in a workflow, distinguishing it from the sibling get_result ('poll with get_result') and from the prepare step ('prepared run'). An agent can tell it apart from both siblings without opening a schema.

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 an explicit precondition ('Call it only after the user explicitly asked to generate'), names the alternative for the follow-up step ('poll with get_result'), and states the auth condition ('the client asks the user to sign in when it is missing'). When-to-call, what-not-to-do, and the next-tool routing are all covered.

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