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

Annotations declare non-read-only, non-destructive, non-open-world, but the description adds genuinely useful behavior the annotations cannot convey: the call is asynchronous, returns a jobId immediately, and results must be polled via get_simulation_status. It stops short of noting cost, runtime, or side effects of running many conversations (personaCount/scenarioCount multiplication).

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 sentences, no waste, with the core action and async/polling behavior front-loaded. Every clause earns its place and the agent can act on it immediately.

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 13-parameter tool with no output schema, the description supplies the missing return-shape context (jobId) and the follow-up polling path, which is the key thing an agent needs. It doesn't note that all parameters are optional or how count parameters combine, but annotations and schema cover the rest adequately.

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 all 13 parameters, defaults, and the enum are already documented in the schema. The description adds persona/scenario framing but no parameter-level meaning beyond that; baseline 3 applies when the schema carries the load.

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 specific verb and resource ('Start async simulated conversations') and the objective ('test how your agent performs against auto-generated or specified personas and scenarios'). This clearly separates it from simulate_ab_test and benchmark_models, though it never names a sibling explicitly.

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 tells the agent what happens next ('use get_simulation_status to poll for results'), which is useful workflow guidance, but offers no when-to-use vs when-not or comparison against alternative simulation tools. Usage context is implied by 'to test how your agent performs' rather than stated.

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