cancel_action

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

With no annotations, the description carries the full behavioral burden. It does usefully disclose a refund of crafting ingredients, but it omits whether the cancel is immediate or queued, whether partial progress is lost, which action categories are cancellable, and whether it errors when idle — significant gaps for a state-mutating control tool.

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?

One sentence, front-loaded with the primary verb and terminating in the notable side effect. No filler or redundant restatement of the name.

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?

Return values are covered by the existing output schema, so the description needn't describe them, and a zero-param tool has little else to specify. The remaining gap is the absence of any state or failure behavior, which matters slightly more here since no annotations supply it.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is empty and fully described. Baseline 4 applies.

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?

"Stop the AI character and cancel its current action" gives a specific verb (stop/cancel) plus the resource (the AI character's in-flight action), and mentions the side effect of returning crafting ingredients. It is clearly distinguishable from siblings like get_action_status or craft, though it never names a sibling explicitly.

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?

Usage is implied: call it when an action is in progress and you want to abort it. There is no explicit guidance on what happens if no action is running, whether it works for every action type (mining, moving, shooting, crafting), or which sibling to consult first to confirm an action exists.

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