training_cancel

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

The description gives rich behavioral detail beyond the annotations: cancelling releases the compute instance, elapsed GPU time is still charged, the most recent checkpoint is preserved, and the operation does not delete the model. This meaningfully supplements the destructiveHint and readOnlyHint annotations and helps the agent anticipate side effects and billing consequences.

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. The first sentence identifies the action and target; the second covers consequences; the third clarifies what the operation does not do. Every sentence earns its place without redundancy or filler.

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 destructive, non-idempotent operation, the description covers the essential context: how to reference the model, what side effects occur, cost implications, checkpoint preservation, and that the model is not deleted. Combined with complete schema coverage and relevant annotations, nothing critical is missing for an agent to invoke the tool 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 100%, so both `model` and `project` are already documented in the input schema. The description restates the accepted reference forms but does not add new parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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 opens with a specific verb and resource: 'Cancel a running training job.' It also distinguishes the tool from siblings by scoping it to training jobs and explicitly stating that stopping is not deletion of the model. This makes the tool's purpose immediately clear and distinct from training_start, training_monitor, and models_delete.

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 clearly explains how to identify the target job via owner/project/model, ul:// URI, or slug with project, and notes the project requirement for slug references. It does not explicitly name alternative tools or when-not-to-use conditions, but the context strongly implies this is the cancellation action for training jobs, so the usage context is clear.

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