Prepare PJM job submission

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

The description says the tool does not submit until confirm_action, implying a non-destructive preview operation. Yet annotations declare destructiveHint=true, which contradicts this. This is a serious inconsistency because the description suggests no state change while the annotation warns of destructive behavior.

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, front-loaded with the key action. It conveys the core behavior and the confirmation step efficiently.

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?

The tool has a complex nested parameter and no output schema, yet the description does not explain the input schema, return format, or usage nuances. The contradiction with annotations further undermines its completeness; the description is insufficient for an agent to confidently invoke this tool.

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 description provides no information about the two parameters (definition and scriptPath) or the nested structure of definition. With schema description coverage at 0%, the description must compensate but does not, leaving the agent without guidance on constructing inputs.

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 previews a normal-batch pjsub operation and returns a confirmation token, distinguishing it from actual submission. It explicitly notes it does not submit until confirm_action, differentiating it from a direct submission tool.

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 explains the tool is a preview step that returns a token for later confirmation. It names confirm_action as the required next step, providing a clear usage flow. However, it does not explicitly contrast with siblings like validate_job or render_job, which could also serve as pre-submission checks.

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