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

Annotations only declare the mutation profile (readOnly false, destructive false, idempotent false, openWorld false); the description goes beyond that by explaining runner behavior (deterministic/adaptive_chat run offline, adaptive_voice requires the voice runtime), admission conditions, and a semantic distinction for caller_environment versus agent ambience. This is meaningful context a caller would not get from the annotations alone.

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 core purpose is front-loaded in the first clause, and the remaining sentences each add distinct operational detail (runner admission, caller_environment semantics). Dense but every sentence earns its place, with 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 mutating tool with 7 parameters, nested objects, and no output schema, the description covers the scenario/runner and caller_environment territory well but omits guidance on other top-level inputs such as policy, default_snapshot_source, organization_id, and what the call returns. It is adequate but leaves clear gaps.

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 low (29%), so the description must carry weight. It adds valuable semantics for the `scenarios` array (runner, language requirements for adaptive_voice) and for caller_environment/noise_level, but leaves several top-level parameters (name, policy, description, organization_id, default_snapshot_source) unexplained, so compensation is only partial.

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 verb (create) and resource (simulation suite) scoped to an AI agent, and clarifies the distinctive behavior that a whole scenario list can be submitted in one call, i.e. 'this is how a scenario pack becomes a suite.' It does not explicitly name the sibling read tools (get_simulation_suite, list_simulation_suites), but the create semantics are unambiguous.

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?

Usage is implied via 'this is how a scenario pack becomes a suite' and the runner admission rules, which tell the caller when a given runner is valid. However, it never explicitly states when to choose this tool over alternatives like preview_simulation_run or start_simulation_run, so the agent must infer the routing.

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