train_delete_job

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

With no annotations, the description fully discloses side effects: deletes output directory unless keep_outputs is true, does not remove LoRA, and requires prior cancellation. This is comprehensive for a mutation 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?

Three sentences, each adding essential information: action and flags, what is not removed, prerequisite and confirmation. No wasted words.

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?

Covers prerequisites, side effects, and exclusions well, but does not mention return value or success indication. For a deletion tool, this is a minor gap.

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 coverage is 100%, but description adds value beyond schema by explaining id originates from train_start and elaborating on keep_outputs' effect on output directory deletion. Slightly elevates above baseline 3.

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 deletes a training job's record and optionally its output directory, distinguishing it from train_cancel (cancellation vs deletion) and noting that the LoRA model is not removed. It specifies the scope as 'cleanup for the Jobs view'.

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?

Explicitly states that running/queued jobs must be cancelled first using train_cancel and that the user should confirm before deleting, providing clear when-to-use and prerequisite guidance.

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