fight

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains the combat loop (walk, shoot, next target), the radius anchoring, and the flee_below retreat threshold. It omits edge cases like what happens when no enemies are found or if the player dies, but covers the core mechanics sufficiently.

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, well-structured sentence that front-loads the primary action and includes critical behavioral details without unnecessary words. Every clause contributes to understanding the tool's operation, making it highly concise 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?

Given that an output schema exists (likely defining job id and status) and the parameter descriptions cover wait_s and replace, the description provides adequate context for the core combat behavior. It does not mention prerequisites like needing a gun equipped (though implied) or failure conditions, but for a combat action with an output schema, it is reasonably complete.

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 provides descriptions for only 2 of 6 parameters (wait_s and replace), giving 33% coverage. The description adds meaning for radius (anchored range) and flee_below (retreat threshold), but does not elaborate on x/y beyond 'around a point' or the interaction with wait_s/replace beyond what the schema already states. It partially compensates for the low schema coverage but not fully.

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 states a specific verb ('Fight') with a clear resource ('visible enemies around a point') and details the behavior ('walks into range, shoots, next target'). It also specifies anchoring to the radius and retreat behavior, making the purpose unmistakable. It distinguishes from siblings like 'defend_area' by focusing on active engagement rather than static defense.

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 usage—fight enemies within a radius using the equipped gun—but does not explicitly state when to choose this over alternatives such as 'defend_area' or other combat tools. There is no exclusionary guidance (e.g., 'use when you want to actively seek enemies' vs 'defend_area' for passive defense), leaving some ambiguity in tool selection.

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