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

Annotations already declare readOnly=false, destructive=false, idempotent=false, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the call is authenticated, execution is asynchronous, and it 'can consume paid model capacity' — a cost warning an agent would otherwise miss. It stops short of explaining failure/retry semantics for the returned 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?

Two short sentences, zero filler, with the core operation stated first and the cost/polling context after. Nothing can be cut without losing information.

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 an async, paid-capacity, non-idempotent creation tool with no output schema, the description covers the essential workflow and cost caveat. The one material omission is that it doesn't say the call returns a run identifier — the very handle the agent needs for the polling step it recommends.

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 100% and all three parameters (task, task_input, idempotency_key) are documented in the schema, including the retry-key behavior. The description adds no parameter-level detail beyond that, so the baseline 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?

States a concrete verb ('Queues') and resource (an authenticated asynchronous task), and the polling/result siblings are named so the agent can place it in the run lifecycle. However, the description never says it creates a *run* of a specific model (the title's 'GPT-6 Astra run' is not reflected), so the resource identity is slightly looser than ideal.

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 an explicit follow-up workflow ('Poll with agentfarm_get_run_status, then read agentfarm_get_run_result'), which routes the agent correctly among siblings. It does not state when *not* to use it or any precondition beyond 'authenticated', but for the only creation tool in the set the guidance is clear.

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