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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that offline runs return synchronously, live direct targets yield a tokenized media WebSocket URL, pstn calls require verified numbers and return 403 NUMBER_NOT_VERIFIED if unverified, and live runs must be polled for terminal state. This is substantial and exceeds typical annotation coverage.

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?

The description is a dense single paragraph but is front-loaded with the two-mode structure and every clause contributes essential info. It avoids fluff and waste. A little more visual structure (bullets or line breaks) would earn a 5, but it remains readable and appropriately sized for the tool's complexity.

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 complex tool with 15 params and no output schema or annotations, the description covers modes, required inputs, transport behavior, error handling, and the polling mechanism. It tells the agent exactly what to pass and how to obtain results. The schema handles parameter details, while the description supplies the contextual glue needed for correct invocation.

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 87%, so the schema already documents most parameters. The description adds value by grouping parameters by mode: transcript/turns/scenarioGoal for offline and targetAgent/goal for live. It also clarifies the behavioral implications of targetAgent transport options, including the 403 error and plan restrictions, going beyond the schema's field descriptions.

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 opens with a clear statement: 'Run a test against a voice agent you control.' It then disambiguates two concrete modes—offline transcript scoring and live synthetic calls—making the tool's function and scope immediately apparent. This distinguishes it from sibling tools like run_demo or test_flow.

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 gives explicit when-to-use guidance for both modes: pass 'transcript' (or 'turns') plus 'scenarioGoal' for offline scoring; pass 'targetAgent' and 'goal' for live calls. It also explains transport-specific constraints (direct vs pstn, plan requirements, verified numbers) and refers to polling via get_run. It doesn't explicitly name alternative tools, but the mode guidance is strong.

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