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

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotence, so the safety profile is covered. The description adds genuinely non-obvious behavior: per-runner runtime admission gates, the language requirement for adaptive_voice, and the explicit disambiguation that caller_environment is synthetic caller-input noise, not the agent's outgoing ambience. Permission requirements and post-create side effects remain unstated.

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?

Three sentences, front-loaded with the core action, then runner behavior, then the caller_environment clarification. Dense but mostly earning its place; the caller_environment sentence partially restates the nested schema description.

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 7-parameter tool with nested objects, no output schema and low schema coverage, the description covers the trickiest path (scenarios/runners/voice) well but leaves the policy object and snapshot source unexplained, so an agent cannot fully call it without inference.

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?

With only 29% schema coverage, the description must compensate, and it does for the scenarios array, runner values and caller_environment/noise_level semantics. However it says nothing about `policy`, the `default_snapshot_source` draft/published choice, or the two required fields, so significant parameters remain undocumented on both sides.

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 ('Create a simulation suite on an AI agent') and adds the framing that a scenario pack becomes a suite via this call. That distinguishes it cleanly from the sibling read tools (get_simulation_suite, list_simulation_suites) and from other create_* tools.

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 real conditional context -- adaptive_voice is 'admitted only where the voice runtime is on', and offline runners are named -- but never frames when to choose this over an alternative (e.g. creating a suite vs. adding scenarios later, or preview_simulation_run/start_simulation_run). Usage is implied rather than routed.

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