step_once

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

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral limit: it submits at most one validated game action, and only conditionally based on local config. But it does not clarify side effects, prerequisites, what 'validated' means, or whether the tool can return without acting.

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 efficient sentence and front-loads the core action. It is not bloated, though its conciseness comes at the cost of important contextual detail.

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 tool that can submit a game action)Skip? The description omits prerequisites, the role of local config, what 'routed decision' means, and how this tool fits with siblings like execute_proposal or autoplay. The output schema helps, but the tool context remains too sparse for confident invocation.

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 0% and the description never mentions route_id. The word 'routed' weakly hints that route_id selects the route, but the tool description does not explain how the parameter influences behavior or what null/default means.

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 names a specific action ('Run one routed decision') and indicates it may submit a game action, so an agent gets a general sense of the tool. However, 'routed decision' is opaque and the description does not distinguish this from siblings like execute_proposal or autoplay, which also appear to advance or execute actions.

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 only usage condition is 'when enabled in local config,' but there is no guidance about when to choose step_once over plan_map_route, recommend_next_action, execute_proposal, or autoplay. No alternatives or exclusions are named.

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