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

The description adds important behavior beyond the annotations: it explicitly warns that the operation 'Bills voice-agent compute' and targets a 'live voice agent', indicating real-world cost and side effects. This complements the destructiveHint=true annotation rather than contradicting it.

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 tight sentences lead with the core action, immediately explain the two parameter-driven modes, then add the crucial cost warning and an API reference. Every clause carries meaning and there is no filler.

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 tool with an output schema and fully documented parameters, the description covers the essential decision points: which mode to use, what happens (grading), and the cost implication. It does not explain asynchronous behavior when wait=false, but the schema already documents wait and max_wait_ms, so this is not a critical gap.

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%, so the schema already documents wait, eval_id, agent_id, and max_wait_ms. The description adds useful context about the two operation modes but does not add new detail beyond the structured schema, 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?

The description states a specific action ('Run'), the exact resource ('single eval scenario' or 'every scenario for an agent'), the target ('live voice agent'), and the outcome ('grade the result'). It clearly distinguishes between eval_id and agent_id modes, so an agent knows what the tool operates on even among many siblings.

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?

The description provides clear usage context: use this tool to execute evaluations and grade results, with either eval_id or agent_id. It does not explicitly state when not to use it or name an alternative tool, but the function is specific enough that an agent can infer when it applies.

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