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

Annotations indicate readOnlyHint=false and destructiveHint=false, signaling a non-read-only mutation that is not destructive. The description confirms this by stating it 'starts' a simulation but does not disclose behavioral consequences such as execution time, whether it returns a simulation ID, or if it triggers an asynchronous process. With annotations covering the basic safety profile, the description adds value by detailing input requirements but stops short of describing the operational outcome. No contradiction with annotations.

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 lengthy but well-structured, with clear bullet points and two full examples. It front-loads the core purpose, then systematically explains the dataset pairings and options. While every sentence adds necessary detail, the length is justified given the complexity; it could be slightly tightened but remains efficient and easy to parse.

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?

The description comprehensively covers all input requirements, including every dataset type, required pairings, and all option fields, with examples. It lacks any description of the return value or output format, which would be expected given there is no output schema. However, for a tool that initiates an action, the input guidance is thorough enough to allow correct invocation. The missing output info is a minor gap.

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 input schema only defines a single 'body' string with a generic 'JSON string of SimulationRequest' description, providing no structural detail. The description compensates fully by detailing the required fields (dataset.type, dataset.source, and their pairings), optional options (maxRecords, baselinePolicyVersionId, includeRuleStats, metricConfig), and even provides concrete JSON examples. This adds substantial meaning beyond the schema and ensures the agent knows exactly how to construct the request.

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 clearly states the tool's action: 'Start an Impact Simulation against historical, uploaded, or inline data.' It specifies the resource (simulation) and the data sources, distinguishing it from sibling simulation tools like lexq_simulation_cancel or lexq_simulation_status. The purpose is unambiguous and action-oriented.

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 provides explicit guidance on when to use each dataset type (HISTORICAL, UPLOADED, MANUAL) with required pairings, and includes detailed examples for uploaded and historical scenarios. It also explains optional parameters like baselinePolicyVersionId and metricConfig, leaving no ambiguity about how to structure a valid request. While it doesn't name alternative tools for other actions, it fully covers the usage context for this specific start operation.

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