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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds real behavioral value by disclosing the default record caps (1000 for HISTORICAL/UPLOADED, unbounded for MANUAL) and the strict type/source pairing constraint, but it never says the run is asynchronous or that a job id must be polled via lexq_simulation_status — a significant omission given the surrounding sibling set.

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?

Purpose is front-loaded, then the mode table and option semantics follow in a scannable structure. The two worked examples are genuinely useful for a JSON-string body parameter, though they restate information already given in prose and add length.

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?

No output schema exists, and the description never states what a successful call returns (simulation/job id, immediate vs. eventual results) or how to follow up. Everything needed to construct the request is present, but the agent is left to infer the response contract from sibling names.

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's only parameter is a tautological 'JSON string of SimulationRequest', so the description carries the entire semantic load and does it well: it enumerates dataset.type/source pairs, the from/to date format and inclusivity, path provenance, manualData shape, and every options field including the metricConfig aggregation object.

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+resource ('Start an Impact Simulation') plus the three data-source modes it accepts. Easily distinguished from siblings like lexq_simulation_status, lexq_simulation_list, lexq_simulation_cancel and lexq_simulation_export, which operate on an already-created simulation.

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?

Gives explicit conditional routing between the three dataset modes (HISTORICAL→EXECUTION_LOGS, UPLOADED→S3_BUCKET, MANUAL→REQUEST_BODY) and points at lexq_dataset_upload as the prerequisite for the uploaded path. It stops short of saying when to prefer this over lexq_dry_run, lexq_dry_run_compare, or lexq_replay_start, which is the remaining gap.

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