edit_training_job

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

The annotations only state destructiveHint=true and readOnlyHint=false. The description goes further by specifying what gets destroyed (the existing config), the exact job states under which destruction is allowed, and the deferral of GPU selection to resume time. This meaningfully clarifies the operation's side effects.

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 sentences with no wasted words. The core purpose is front-loaded, and each subsequent sentence adds essential constraints or sequencing information. The structure is easy to parse and act on.

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 mutation tool with no output schema, the description covers the core action, state preconditions, name-matching constraint, and the required resume step. It falls slightly short on error behavior and a precise definition of config_file format, but is otherwise sufficient for an agent to invoke it 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 coverage is 0%, so the description must compensate. It does clarify that config_file is the new YAML and that config.name inside it must match the original job's name, but it does not explicitly define job_id or specify whether config_file is a path or inline content. Meaning is added, but not complete for both parameters.

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 'Replace the config of a non-running training job', a crisp verb+resource+scope statement. It is clearly distinguishable from siblings like submit_training_job, cancel_training_job, and resume_training_job, and is reinforced by the concrete endpoint it backs.

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?

Explicit preconditions are given, including only working when the job is STOPPED, CANCELED, or FAILED, and the requirement that config.name must match the original job's name. It also directs the agent to call resume_training_job afterwards, making the expected sequence explicit.

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