stop_training

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

With no annotations to rely on, the description carries the behavioral disclosure burden and does so well: it reveals that SIGINT is sent, that the model is saved, and that after timeout the process is force-killed. This gives an agent a clear understanding of side effects and shutdown semantics, though it does not mention other potential effects on logs, state, or child processes.

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 compact and front-loaded, with the primary behavior in the first sentence and parameter details in a short list. Every sentence contributes useful information, and there is no filler or repeated schema content.

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 two-parameter, single-action tool, the description is largely complete: it explains what happens on stop, what timeout does, and the parameters are fully documented. The presence of an output schema covers return-value expectations, and the only notable gap is the lack of explicit guidance on when to choose this tool over related siblings.

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 explain the parameters, and it does. run_id is defined as "The run to stop," and timeout is defined as "Seconds to wait for graceful shutdown before force-killing," adding meaningful behavioral meaning beyond the bare schema titles.

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 and resource: "Gracefully stop a running training run," and adds the concrete mechanism "sends SIGINT so the model is saved." This clearly differentiates the tool from siblings like resume_training and force_training by emphasizing graceful behavior and signal-based stopping.

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 the tool is used when a training run is running and needs a graceful stop, and it introduces "force-killing" as the fallback after timeout. However, it does not explicitly state when to prefer this tool over alternatives such as force_training or cleanup_processes, nor does it list conditions where it should not be used.

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