training_cancel

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description goes further by disclosing that the compute instance is released, elapsed GPU time is still charged, and the most recent checkpoint is preserved rather than discarded – genuine side-effect detail beyond the annotations.

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?

Three sentences, front-loaded with the action and reference forms before the side-effect details. Every sentence earns its place, though the closing 'does not delete the model' is slightly redundant with the checkpoint-preservation statement.

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 cancel tool with no output schema, the description covers the reference forms, compute release, billing behavior, and checkpoint preservation. It omits permissions/auth requirements, but is otherwise complete enough to call 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 parameters are already documented. The description restates the accepted reference forms (owner/project/model, ul:// URI, or slug with project) but adds no syntax or format detail beyond the schema, so the baseline 3 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?

States a specific verb ('Cancel') and resource ('a running training job'), and explicitly distinguishes itself from deletion with 'This stops the job and does not delete the model.' This clearly separates it from siblings like 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 clarifies scope (stops but does not delete), which implicitly routes deletion to models_delete, and explains the accepted reference forms. However, it never explicitly states when to use this versus alternatives or any preconditions (e.g. job must be running), leaving usage to inference.

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