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

The description reveals important behavioral traits beyond the annotations: saving has no cost and starts nothing, refusals occur for specific invalid inputs, refusal messages name the limit, and launchBlockers do not prevent saving. Since annotations are all false/uninformative, the description carries the burden and does so richly.

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 dense sentences carry a large amount of actionable information with no filler. The most important side-effect statement is front-loaded, followed by validation semantics and user-handling guidance. Every sentence earns its place.

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 create tool with no output schema, the description covers side effects, validation failures, the response summary's launchBlockers, and a pointer to relevant documentation. However, it does not explain how to source or validate projectId, nor name the exact response field for the dashboard link, leaving minor gaps an agent must infer.

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?

The schema already documents populations and stages in detail, but top-level projectId has no description and name only has a trivial one. The description adds meaningful operational constraints: loadEngineId must come from list_engines, stages must meet minimum duration, and bot/population counts are subject to account limits. This compensates for schema gaps, though it does not enumerate every parameter.

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 'Create a scenario in a project,' a specific verb and resource that clearly identifies the tool's function. The resource 'scenario' is distinct from sibling create_* tools, so an agent can select it without opening the schema. The added context about saving not starting anything further sharpens the purpose.

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 clear context: saving is cheap and inert, so the agent should hand the user the dashboard link and let the user launch the scenario. It also instructs how to handle launch blockers. However, it does not explicitly name alternative tools or state when *not* to use this tool, so it stops short of full exclusion guidance.

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