kill_action

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

The description directly contradicts the annotation readOnlyHint=true. Killing an action is a state-changing operation, not read-only. The description attempts to reframe it as a safety stop, but it still modifies execution state, so this is a serious inconsistency.

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 three focused sentences, front-loaded with the action, and contains no unnecessary information. Every sentence adds value regarding either the precondition, outcome, or safety posture.

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?

The description covers the core behavior, precondition, return statuses, and clarifies safety. However, it does not explain how to obtain the execution_tracking_id, and the annotation contradiction creates ambiguity. The presence of an output schema partially offsets the need to describe return values in detail.

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 single parameter execution_tracking_id is explained in the description as the identifier used to kill the action. It also adds context about the action needing to be running and references the can_kill field, which compensates for the 0% schema description coverage.

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's purpose: "Kill a currently running OliveTin action by its execution_tracking_id." It uses a specific verb ("kill"), identifies the resource ("currently running OliveTin action"), and distinguishes it from sibling tools like restart_action or get_execution_status.

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 provides a clear precondition: "Only works when the LogEntry's can_kill field is true." It also explains the outcome statuses, but it doesn't explicitly mention alternatives or exclusions relative to sibling tools, so it stops short of a full guidance score.

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