attack

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

With no annotations, the description carries the full burden, but it does disclose one genuine behavioral trait: the attack is continuous (versus a single strike). It omits whether range/proximity is required, what happens if the target is invalid or out of range (attack_range exists as a sibling), and any cooldown or cost.

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?

A single short sentence with the action front-loaded and the parenthetical constraint appended efficiently. Nothing is wasted, though it is arguably too terse for the behavioral gaps it leaves open.

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 simple one-parameter game action with no output schema this is minimally viable, but it leaves out range/proximity requirements and the relationship to attack_range and stop_attack, which an agent would need to invoke it correctly.

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%, so the description must compensate. 'by ID' clarifies that target_id is an identifier of a being rather than, say, an item, which is useful, but it adds no format, range, or validity detail beyond that.

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 ('Attack'), the resource ('a being'), and the identifying mechanism ('by ID'), which maps cleanly onto target_id. It does not explicitly differentiate from the obvious sibling stop_attack, but the core action is unambiguous.

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?

There is no guidance on when to use this versus alternatives like stop_attack or attack_range, nor any prerequisites (e.g., target must be in range). Usage must be inferred entirely from the tool name.

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