Run one engagement

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

Annotations declare readOnlyHint=true, indicating no side effects. The description adds valuable behavioral context: determinism (same seed replays identically), notional data, and details of the returned record. There is 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 a single, front-loaded sentence that efficiently conveys purpose and output content. It enumerates many output fields without excess verbiage, though it could be more structured (e.g., bullet points).

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?

Given the tool's complexity (many nested parameters, no output schema), the description thoroughly lists the output content (winner, timeline, fix quality, LOB counts, etc.) and warns about notional data. It also directs users to get_config_schema for parameter details, covering all essential context.

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 100%, so the baseline is 3. The description does not add parameter-level meaning beyond the schema's detailed descriptions and example seeds. The config_overrides parameter references get_config_schema, which is helpful.

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 runs a single deterministic force-on-force engagement and returns the full record. It specifies the exact resource (engagement), verb (run), and scope (single), distinguishing it from sibling tools like sweep_seeds which imply multiple runs.

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 implies use for single engagement simulations versus sweeps via the word 'single', but it does not explicitly state when to use this tool vs siblings like sweep_seeds or compare_configs. No when-not-to-use guidance is provided.

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