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

Annotations indicate readOnlyHint=false (mutation) and openWorldHint=true (external effects). The description adds that it starts a training run on an isolated cloud GPU, which conveys resource usage. However, it does not describe any side effects (e.g., billing, cancellation, or what happens on failure). Given that annotations already cover the safety profile, the description provides enough but not rich behavioral context.

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 two sentences with no filler. The critical precondition is front-loaded, and the action is stated clearly. Every word adds value.

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?

Given the tool has only one parameter and an output schema exists, the description covers the essential precondition and the action. It tells the agent exactly when to invoke it and what it does. It could explicitly state that jobId is the identifier from create_image_training_job, but the reference is implicit. Overall, the description is complete enough for correct invocation.

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?

The schema provides only a jobId string with no description, and schema coverage is 0%. The description indirectly implies jobId comes from create_image_training_job ('from create_image_training_job' refers to the upload URLs, but the job ID is part of that context). However, it does not explicitly state that jobId is the ID returned by create_image_training_job, so the description adds some meaning but does not fully compensate for the missing parameter documentation.

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 action ('Starts') and the resource ('isolated cloud GPU training run'), and the tool name specifies 'image training' to differentiate from generic start_training. The precondition referencing create_image_training_job further clarifies that this is the second step in an image-training workflow, so an agent can distinguish it from other start tools.

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 explicitly states when to use the tool: 'Use this only after every image was successfully PUT to its upload URL from create_image_training_job.' This gives a clear precondition and names the prerequisite tool. It implicitly tells the agent not to use it before that step, which is strong usage guidance.

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