Template detail

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

Annotations already cover read-only, open-world, and non-destructive behavior. The description adds value by disclosing the return envelope ({ok, message, next_tool, next_args, ...}) and the fact that the tool tells you how to proceed once the workload is online.

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?

Two sentences, no filler, with the core purpose front-loaded and the return shape following immediately. Every clause contributes useful information.

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?

With a single well-documented parameter, a rich output schema, and annotations covering safety, the description is complete. It also flags the next_tool/next_args continuation mechanism, which is critical for an agent driving a multi-step workflow.

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 covers the single template parameter at 100% including an example, so the description does not need to add parameter syntax. It provides only indirect context by framing the parameter as a workload, which is adequate but not extra semantic value.

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 is specific: 'Full detail for one workload' identifies the resource and scope, and the enumerations (weight files, hardware gates, drive instructions) make it unmistakable. The singular 'one workload' separates it from list-oriented siblings like list_templates and list_gpus.

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 makes the usage context clear: use this when you need complete detail about a single workload/template. It does not explicitly name alternatives or exclusions, but the singular scope and the mention of next_tool/next_args strongly imply a selection-and-drill-down flow.

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